System

Abstract

A system is provided.SOLUTION: A system for suggesting an optimal time for a child to fall asleep, comprising: means for collecting sleep activity information; means for analyzing a child's Children's Day rhythm and tendency to fall asleep based on the collected information; means for generating a timeline for preparation before falling asleep based on a result of the analysis; and means for notifying a user of the generated timeline.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In modern society, lack of sleep among children has become a serious problem. It is particularly difficult for parents to determine their child's optimal sleep time and manage their daily lives accordingly. Therefore, there is a need for a system that can advise parents on the optimal sleep time based on their child's individual sleep rhythm and tendencies. It is also important for parents to provide advice on preparing meals and bathing at appropriate times. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means.

[0006] This system proposes an optimal time for a child to fall asleep. The system includes: a means for collecting a child's daily activity data; a means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data; a means for generating a timeline of preparations before falling asleep based on the analysis results; and a means for notifying a user of the generated timeline on their device. Specifically, the system collects the child's activity data using an activity tracker and a life log application, stores the data in a database, and cleanses it. Furthermore, the system analyzes the child's sleep rhythm and sleep onset tendency using a machine learning algorithm to calculate the optimal time for falling asleep. The system then generates a timeline for preparing meals and baths based on the analysis results and notifies the parent's device, allowing the parent to prepare the child for sleep at the appropriate time.

[0007] "Child" refers to a minor whose sleep rhythm and activity data is managed by the system.

[0008] "Optimal sleep time" refers to the optimal time to go to bed for that day, calculated based on individual sleep rhythms and activity data.

[0009] "System" refers to a comprehensive configuration including a computer program and related hardware that performs a series of processes such as collecting, analyzing, and notifying children's activity data.

[0010] "Daily activity data" is information about a child's daily life, and includes data such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times.

[0011] "Collection methods" refers to activity trackers, smartphone applications, and other devices or software used to capture a child's daily activity data.

[0012] "Means for analysis" refers to algorithms and related software for processing collected daily activity data and analyzing individual sleep rhythms and sleep onset trends.

[0013] "Means for generating a timeline" refers to software and algorithms that use the analysis results to create a schedule of preparatory activities (e.g., meals, bathing) for optimal sleep onset times.

[0014] "Means of notification" refers to the communication means and software for sending the generated timeline and advice to the user's (parent's) device and displaying it.

[0015] "Database" refers to a structured data storage system for storing collected daily activity data and facilitating access and analysis.

[0016] "Cleansing" refers to the process of correcting outliers and missing data from collected data and removing errors.

[0017] "Machine learning algorithms" refer to computational models and methods that learn patterns from past data and predict optimal sleep onset times in the future. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] MODE FOR CARRYING OUT THE INVENTION

[0040] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and an embodiment thereof will be described below.

[0041] System configuration

[0042] The system includes means for collecting data on a child's daily activities, means for analyzing the collected data, means for generating a timeline from the analysis results, and means for notifying the child of the generated timeline.

[0043] Specific examples of programs

[0044] 1. Data Collection

[0045] server

[0046] The server periodically collects children's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from activity trackers and smartphone apps.

[0047] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[0048] 2. Data Analysis

[0049] server

[0050] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[0051] As a specific example, data from the past few weeks is used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops).

[0052] 3. Timeline generation

[0053] server

[0054] Based on the analysis results, the server calculates the optimal time to fall asleep for that day.

[0055] Next, the system calculates backwards based on the optimal time to fall asleep and generates a timeline for preparations before falling asleep (eating, bathing, etc.).

[0056] For example, if the optimal time to fall asleep is 8:30 p.m., create a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[0057] 4. Notification

[0058] Terminal

[0059] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app.

[0060] For example, the app will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[0061] User

[0062] Parents can monitor their child's life by checking the app's notifications and following the suggested schedule.

[0063] Parents act as if they start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30.

[0064] As described above, the system works in conjunction with the server and devices to calculate the optimal time for a child to fall asleep and help parents prepare for sleep appropriately. This system allows parents to alleviate their children's sleep deprivation and ensure a healthy lifestyle.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] User

[0068] The user (parent) launches the smartphone app and sets up a child's account by entering basic information such as the child's name, age, and gender.

[0069] Step 2:

[0070] Terminal

[0071] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[0072] Step 3:

[0073] server

[0074] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[0075] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[0076] Step 4:

[0077] server

[0078] The server uses machine learning algorithms to analyze the child's sleep rhythm and sleep onset tendency based on data from the past few weeks.

[0079] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[0080] Step 5:

[0081] server

[0082] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[0083] Step 6:

[0084] server

[0085] Based on the optimal time to fall asleep calculated by the server, a timeline of preparations before falling asleep (eating, bathing, etc.) is generated.

[0086] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[0087] Step 7:

[0088] server

[0089] The server pushes the generated timeline to the parent's smartphone.

[0090] Step 8:

[0091] Terminal

[0092] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[0093] For example, it will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[0094] Step 9:

[0095] User

[0096] Parents can check app notifications to help their children get ready for sleep.

[0097] Specifically, start preparing dinner at 18:30, feed dinner at 19:00, and give the baby a bath at 19:30.

[0098] This allows the system to help children maintain optimal sleep rhythms and allows parents to manage their children's lives at the appropriate time.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] It is known that lack of sleep in children has a negative impact on their growth and learning ability. However, it is difficult to find a sleep time that is appropriate for each child's daily rhythm. With conventional methods, parents often rely on experience and intuition to determine their child's sleep time, and there is a lack of means to derive the optimal sleep time based on scientific data analysis. Cleansing the collected data and appropriately setting notification timing are also challenges.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes means for collecting data on the child's daily activities, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for calculating an optimal sleep onset time from the analysis results and generating a timeline for preparations before falling asleep, means for notifying a user's terminal of the generated timeline, and means for sending a notification based on the timeline to encourage the user to prepare the child for sleep. This allows the server to suggest an optimal sleep onset time for each child based on scientific data analysis and to notify parents of the notification so that they can appropriately prepare for sleep.

[0104] - "Children's daily activity data" refers to data that indicates the movements and physical indicators of children in their daily lives, including the number of steps taken, amount of exercise, heart rate, meal times, bathing times, etc.

[0105] An "activity tracker" is a device used to measure and collect data on a child's physical activity, such as a smartwatch or fitness tracker.

[0106] A "life log application" is a software application for recording and managing various data about a child's daily life.

[0107] "Data cleansing" is the process of correcting outliers and missing data from a collected dataset to build an accurate dataset.

[0108] "Database" refers to a system for organizing and storing information, and for safely and efficiently storing and managing collected activity data.

[0109] "Sleep rhythm" refers to a child's daily sleep patterns and cycles, and usually indicates the tendency for sleep onset and wakefulness times over a certain period of time.

[0110] "Sleep tendency" indicates the tendency of a child to fall asleep easily under what conditions or circumstances.

[0111] The "timeline" calculates the optimal time to fall asleep and shows a specific schedule for making various preparations before falling asleep.

[0112] A "machine learning algorithm" is a method by which a computer learns patterns from data and makes predictions and classifications, and in this invention it is used to analyze sleep rhythms and sleep onset tendencies.

[0113] A "notification" is a message or alert that notifies a user of specific information, and includes push notifications from applications displayed on a device.

[0114] MODE FOR CARRYING OUT THE INVENTION

[0115] The present invention is a system for proposing an optimal time for a child to fall asleep, in which a server, a terminal, and a user play their respective roles, and is specifically implemented as follows.

[0116] System configuration

[0117] server

[0118] The server uses activity trackers (e.g., smartwatches or fitness trackers) and life log applications (e.g., health apps on smartphones) to collect data on the child's daily activities.

[0119] The server cleanses the collected data, correcting outliers and missing data to build an accurate dataset, improving data quality and increasing the reliability of analysis results.

[0120] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's sleep rhythm and sleep onset tendency, using Python libraries such as Scikit-learn and TensorFlow.

[0121] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then calculates backwards from the optimal time to fall asleep and generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner begins at 6:30 p.m. and bathing ends at 7:30 p.m.

[0122] Terminal

[0123] The parent's smartphone (device) receives push notifications sent from the server. The notifications include a timeline and specific advice for optimally preparing the child for sleep. For example, the app displays alerts such as "Start preparing dinner at 6:30 PM," "Dinner at 7:00 PM," and "Start preparing for bath time at 7:30 PM."

[0124] User

[0125] Parents can check the app's notifications and manage their children's lives according to the suggested schedule. For example, parents can start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. This will improve the quality of their children's sleep and ensure a healthy daily rhythm.

[0126] Specific examples

[0127] The specific analysis method involves extracting average sleep onset times and sleep patterns using data from the past few weeks. For example, a timeline can be generated by following the steps below.

[0128] Collecting exercise and heart rate data

[0129] Cleansing the data and storing it in the database

[0130] Analysis using machine learning algorithms

[0131] Calculating the optimal time to fall asleep

[0132] Creating a timeline for preparation before falling asleep

[0133] Push notifications to devices

[0134] Prompt Sentence Examples

[0135] Here are some examples of prompts to input to a generative AI model:

[0136] markdown

[0137] The system collects data on your child's daily activities and suggests the optimal time for them to fall asleep. It analyzes the collected data and calculates the optimal time for them to fall asleep for that day. For example, it generates a timeline like this:

[0138] 18:30 Start preparing dinner

[0139] 19:00 Dinner

[0140] 19:30 Start preparing for bathing

[0141] Sticking to this schedule will improve the quality of your child's sleep.

[0142] Specific timeline

[0143] Below is an example of a timeline generated by the system:

[0144] Dinner starts at 18:30

[0145] Bathing starts at 19:30

[0146] Using these prompts, the generative AI model can provide a specific timeline, allowing parents to find the optimal time for their child to fall asleep and make appropriate preparations.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1:

[0149] The server collects data on children's daily activities. Specifically, it collects data using activity trackers (e.g., smartwatches and fitness trackers) and life log applications (e.g., smartphone health apps). As input, it receives data from each device, such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times. As output, it temporarily stores this data.

[0150] Step 2:

[0151] The server cleanses the collected data. Cleansing includes correcting outliers and missing data. For example, it identifies obviously abnormal or missing values ​​from the collected data and corrects or removes them in an appropriate way. The collected daily activity data is used as input. The output is a cleansed, accurate data set.

[0152] Step 3:

[0153] The server stores the cleansed data in a secure database. The database includes a means for efficiently storing and managing the acquired activity data. The cleansed data is used as input. The output is the data stored in the secure database.

[0154] Step 4:

[0155] The server analyzes the child's sleep rhythm and sleep onset tendency based on the collected daily activity data. A machine learning algorithm is used for the analysis. Specifically, Python's Scikit-learn and TensorFlow are used to extract the child's average sleep onset time and sleep onset pattern from each data point. The daily activity data stored in the database is used as input. The analysis results of the sleep rhythm and sleep onset tendency are obtained as output.

[0156] Step 5:

[0157] The server calculates the optimal time to fall asleep for that day based on the analysis results and generates a timeline for preparations before falling asleep. For example, if the optimal time to fall asleep is 8:30 PM, a timeline is created in which dinner begins at 6:30 PM and bathing ends at 7:30 PM. The analysis results are used as input, and a specific timeline is generated as output.

[0158] Step 6:

[0159] The server notifies the user's device of the generated timeline. The device may be a parent's smartphone. The server sends a push notification using a service such as Firebase Cloud Messaging (FCM). The generated timeline is used as input. The notification is sent to the device as output.

[0160] Step 7:

[0161] The parent (user) checks the notification on the smartphone (device) and manages the child's life according to the suggested schedule. For example, based on the device notification, the parent may start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. The timeline notification displayed on the device is used as input. The output is the execution of the child's life management.

[0162] By carrying out the above steps in sequence, it is possible to build a system that suggests the optimal time for a child to fall asleep and allows parents to make appropriate preparations.

[0163] (Application example 1)

[0164] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0165] Conventional systems that suggest optimal sleep times for children have problems with insufficient data collection and analysis, making it difficult to accurately grasp individual sleep rhythms and sleep onset tendencies. Furthermore, if notifications of preparation schedules before bedtime are not effective, it is difficult for parents to take appropriate action, preventing the maintenance of a healthy lifestyle rhythm for their children. Therefore, there was a need for a system that could provide more accurate notifications that were easy for users to understand.

[0166] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0167] In this invention, the server includes means for collecting daily activity data of a child, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for notifying a user's device of the generated timeline, means for sending a push notification to the user's device, and means for analyzing data using a machine learning algorithm. This makes it possible to accurately analyze a child's individual sleep rhythm and effectively notify parents of the optimal time to fall asleep and the preparation schedule before that time.

[0168] "Children's daily activity data" refers to data on activities that children perform in their daily lives, and includes information such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times.

[0169] "Collection methods" refers to devices or software used to collect data on a child's daily activities, such as activity trackers or life logging applications.

[0170] "Means for analysis" refers to devices or software that analyze a child's sleep rhythm and tendency to fall asleep based on the collected data, and may specifically use machine learning algorithms.

[0171] "Means for generating a timeline" refers to a device or software for creating a preparation schedule before falling asleep based on the analysis results.

[0172] "Means for notifying" refers to devices or software for notifying the user's device of the generated timeline, and includes push notifications.

[0173] "User's terminal" refers to a device such as a smartphone or tablet used by a user.

[0174] "Means for sending push notifications" refers to devices or software that send messages in real time from a server to a user's device, such as a smartphone.

[0175] "Means for analyzing data using machine learning algorithms" refers to devices or software that use artificial intelligence technology to accurately predict and analyze a child's individual sleep rhythm and sleep onset tendency based on collected data.

[0176] The present invention relates to a system for suggesting an optimal time for a child to fall asleep, and an embodiment thereof will be described in detail below.

[0177] System configuration

[0178] Data collection

[0179] Activity trackers and lifelogging applications are used to collect data on children's daily activities, which periodically transmit data such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times to a server. The server stores the collected data in a secure database and performs data cleansing. Data cleansing involves correcting outliers and missing data to build an accurate dataset.

[0180] Data analysis

[0181] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency. Specifically, machine learning frameworks such as TensorFlow are used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops) from data from the past few weeks.

[0182] Timeline Generation

[0183] Based on the analysis results, the server calculates the optimal time to fall asleep for that day. Then, by working backwards from the optimal time, it generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[0184] notification

[0185] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app. For example, the app can display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30." Parents can check the app's notifications and manage their children's lives according to the suggested schedule. This allows parents to prevent their children from getting enough sleep and ensure a healthy lifestyle.

[0186] Examples and prompts

[0187] For example, based on data recorded by an activity tracker, the following schedule could be sent to a parent's smartphone.

[0188] Example prompt:

[0189] "Analyze your child's sleep rhythm and create a timeline for optimal sleep onset."

[0190] This system allows parents to receive specific instructions in real time, such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30," enabling them to effectively manage their children's daily rhythms.

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] The server collects children's daily activity data from activity trackers and lifelogging applications. The collected data includes the number of steps, exercise volume, heart rate, meal times, bath time, etc. This data is sent to the server via the network. The input is the raw data from the activity trackers and lifelogging applications, which is then stored in a secure database.

[0194] Step 2:

[0195] The server cleanses the collected daily activity data. As part of the cleansing process, it corrects outliers and missing data to build an accurate dataset. Specifically, it performs operations such as deleting values ​​outside the data range and filling in missing values ​​with the average value. The input is the raw data collected in step 1, and the output is a cleansed, accurate dataset.

[0196] Step 3:

[0197] The server then uses machine learning algorithms to analyze the cleansed data. Specifically, it uses frameworks such as TensorFlow to analyze the child's sleep rhythm and sleep onset tendency. Data from the past few weeks is used as input to extract the child's average sleep onset time and sleep onset pattern. The output is the analysis results of sleep onset tendency and sleep onset pattern.

[0198] Step 4:

[0199] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then works backwards from this optimal time to generate a preparation schedule before falling asleep. For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner starts at 6:30 p.m. and bathing finishes at 7:30 p.m. The input is the analysis results obtained in step 3, and the output is a specific preparation schedule.

[0200] Step 5:

[0201] The server pushes the generated preparation schedule to the user's device. Specifically, it sends notifications to the parent's smartphone with content such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30." The input is the preparation schedule generated in step 4, and the output is the notification content displayed on the user's device.

[0202] Step 6:

[0203] Users can check notifications on their smartphones and manage their children's lives according to the suggested schedule. For example, parents can ensure their children fall asleep at the optimal time by starting dinner preparation at 18:30, feeding them at 19:00, and starting bathing at 19:30. The input is the notification content on the device, and the output is the child's healthy lifestyle rhythm.

[0204] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0205] MODE FOR CARRYING OUT THE INVENTION

[0206] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and embodiments thereof will be described below. In particular, by combining it with an emotion engine that recognizes the user's emotions, further effects can be provided.

[0207] System configuration

[0208] The system includes a means for collecting data on a child's daily activities, a means for analyzing the collected data, a means for generating a timeline from the analysis results, a means for notifying the user of the generated timeline, and an emotion engine for recognizing the user's emotions.

[0209] Specific examples of programs

[0210] 1. Data Collection

[0211] server

[0212] The server periodically collects the child's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app.

[0213] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[0214] 2. Data Analysis

[0215] server

[0216] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[0217] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[0218] 3. Calculating the optimal time to fall asleep

[0219] server

[0220] Based on the analysis results, the server calculates the optimal time to fall asleep for that day by combining the average time to fall asleep obtained from past data with the activity data for that day.

[0221] 4. Timeline generation

[0222] server

[0223] The server generates a timeline of preparations before falling asleep (eating, bathing, etc.) based on the optimal time to fall asleep.

[0224] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[0225] 5. Emotional Engine Adjustment

[0226] server

[0227] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[0228] The server takes into account the emotion engine's analysis and fine-tunes the timeline, for example, if a child feels stressed during a certain time period, it will add relaxation activities during that time.

[0229] 6. Notification

[0230] Terminal

[0231] The parent's smartphone receives push notifications from the server and displays the schedule and advice on the app.

[0232] Specifically, alerts will be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[0233] 7. Feedback

[0234] User

[0235] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[0236] Parents engage in relaxation activities with their children (e.g., reading aloud, playing music).

[0237] Parents enter feedback into the app, reporting any problems encountered during implementation and their child's emotional state.

[0238] 8. Processing Feedback

[0239] server

[0240] The server receives feedback from the parents and stores it in a database.

[0241] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[0242] In this way, the system maintains an optimal sleep rhythm for children through collaboration between the server, device, and user, and enables flexible responses to emotional situations through the emotion engine, thereby realizing health management for children and the establishment of a comfortable daily rhythm.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] User

[0246] Parents launch the smartphone app and set up their child's account by entering basic information such as their child's name, age, and gender.

[0247] Step 2:

[0248] Terminal

[0249] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[0250] Step 3:

[0251] server

[0252] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[0253] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[0254] Step 4:

[0255] server

[0256] The server analyzes the child's sleep rhythm and sleep onset patterns based on data from the past few weeks, and machine learning algorithms identify patterns of decreased heart rate and decreased physical activity at certain times of the day.

[0257] Step 5:

[0258] server

[0259] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[0260] Step 6:

[0261] server

[0262] The server generates a timeline for preparations before falling asleep (e.g., meals and bathing) based on the optimal time to fall asleep. For example, if the patient falls asleep at 8:30 PM, the server creates a schedule for dinner at 6:30 PM and bathing at 7:30 PM.

[0263] Step 7:

[0264] server

[0265] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[0266] The timeline is fine-tuned based on the emotion engine's analysis: for example, if a child is feeling stressed, add relaxation activities during that time.

[0267] Step 8:

[0268] server

[0269] The server pushes the generated timeline to the parent's smartphone.

[0270] Step 9:

[0271] Terminal

[0272] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[0273] For example, alerts could be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[0274] Step 10:

[0275] User

[0276] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[0277] For example, start preparing dinner at 18:30, feed dinner at 19:00, and bathe at 19:30. Additionally, if your child is feeling stressed, engage in relaxation activities (e.g., reading aloud, playing music).

[0278] Step 11:

[0279] User

[0280] Parents enter feedback into the app, reporting ongoing issues and their child's emotional state.

[0281] Step 12:

[0282] server

[0283] The server receives the feedback from the parents and stores it in a database.

[0284] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[0285] This allows the system to help children maintain optimal sleep rhythms and parents to manage their children's lives at the appropriate time.The emotion engine also enables flexible responses according to emotional situations.

[0286] Example 2

[0287] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0288] Current child sleep schedule management systems do not adequately consider a child's individual sleep rhythm or emotional state. Furthermore, there are many challenges in analyzing collected data and reflecting it in the timeline. As a result, parents struggle to find the optimal time for their child to fall asleep, which can have a negative impact on the child's health. The present invention aims to flexibly adjust the optimal sleep time and timeline based on the child's daily activity data and emotional data, and provide parents with accurate notifications.

[0289] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting daily activity data of a child, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep from the analysis results, means for fine-tuning the generated timeline taking emotions into consideration, means for notifying the user's terminal of the generated timeline, and means for collecting and processing feedback from the user. This makes it possible to propose a flexible schedule according to the individual situation of each child, and ensure the optimal time for falling asleep.

[0290] "Children's daily activity data" is information about the activities that children perform in their daily lives, including the number of steps, amount of exercise, heart rate, meal times, bath times, and the like.

[0291] "Data cleansing" is the process of correcting outliers and missing data in collected data to build an accurate and usable dataset.

[0292] A "database" is a system for storing and managing collected data, allowing necessary information to be retrieved efficiently.

[0293] "Sleep rhythm" refers to a child's sleep-wake pattern over a period of time, a cycle based on their natural biological clock.

[0294] "Sleep onset tendency" refers to the pattern or tendency of when and under what circumstances a child falls asleep.

[0295] A "timeline" is a timetable that indicates the best times to perform certain events or activities, including preparation steps before falling asleep.

[0296] The "emotion engine" is a system that recognizes emotions from a child's facial expressions and voice data, allowing it to analyze their emotional state.

[0297] "Fine-tuning" means flexibly modifying the generated timeline based on new information such as the analysis results of the emotion engine.

[0298] A "terminal" is a device that receives notifications and information from a server and displays them to the user, and includes smartphones, tablets, etc.

[0299] "Feedback" refers to opinions and impressions provided by users, as well as information about problems and emotional states during execution.

[0300] A "machine learning algorithm" is a computational method that automatically learns specific patterns and trends from data and makes predictions and classifications for new data.

[0301] The present invention provides a system for proposing an optimal sleep time for a child, and an embodiment thereof will be described in detail below. The system collects and analyzes a child's daily activity data to generate an optimal sleep time and a timeline for achieving this. It also includes a means for appropriately adjusting the timeline, taking into account the child's emotional state. This system promotes health management and optimization of the child's daily rhythm.

[0302] System configuration

[0303] The system consists of the following main components:

[0304] 1. Means of collecting data on children's daily activities

[0305] 2. How to cleanse and store the collected data in a database

[0306] 3. A means of analyzing children's sleep rhythms and sleep onset tendencies based on collected data

[0307] 4. A method for generating a timeline of preparations before falling asleep from the analysis results

[0308] 5. A means to collect emotional data and fine-tune the timeline through an emotional engine

[0309] 6. A method for notifying the user of the generated timeline

[0310] 7. How to collect and process user feedback

[0311] Data Collection and Cleansing

[0312] server

[0313] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and lifelogging applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath times, etc. The collected data is stored in a secure database. A data cleansing process corrects outliers and missing data to build an accurate dataset.

[0314] Data analysis and calculation of optimal sleep onset time

[0315] server

[0316] The server analyzes the collected daily activity data using machine learning algorithms (e.g., random forests and neural networks). This analysis allows the server to understand the child's sleep rhythm and sleep onset tendency. For example, it identifies patterns of decreased heart rate and reduced physical activity at certain times of the day. Based on this, the server calculates the optimal time for the child to fall asleep.

[0317] Creating and adjusting timelines

[0318] server

[0319] The server generates a timeline based on the optimal time to fall asleep, including preparation steps before falling asleep (e.g., dinner, bath, etc.). For example, to fall asleep at 8:30 p.m., it creates a schedule such as dinner at 6:30 p.m. and bath time at 7:30 p.m. Furthermore, it analyzes emotional data collected by the emotion engine (e.g., obtained using a camera or microphone) and fine-tunes the timeline. If a child feels stressed in the evening, it adds relaxation activities (e.g., listening to music) to that time period.

[0320] Schedule notifications and feedback

[0321] Terminal

[0322] The parent's smartphone receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath time at 19:30," and "Relaxation time at 20:00." Users can enter feedback through the app to report any problems encountered during execution and their child's emotional state.

[0323] server

[0324] The server stores and analyzes parent feedback in a database. This feedback data is used to improve future schedule suggestions and adjust the emotion engine. For example, the effectiveness of relaxation activities can be evaluated to improve the accuracy of future suggestions.

[0325] Examples of concrete examples and prompts

[0326] For example, the following prompt sentence is input to the generative AI model:

[0327] "My child has been waking up late recently. Can you suggest an optimal time for him to fall asleep?"

[0328] "Tell me about relaxation activities to help reduce my child's stress levels."

[0329] This system allows the server, device, and user to work together to maintain a child's optimal sleep rhythm and respond flexibly to their emotional state, thereby helping to manage a child's health and establishing a comfortable daily rhythm.

[0330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0331] Step 1:

[0332] Data collection

[0333] server

[0334] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and life log applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath time, etc. Specifically, the server obtains data from each device through an API and stores it in a secure database.

[0335] Input: Raw data from activity trackers and life logging applications

[0336] Output: Daily activity data stored in a secure database

[0337] Step 2:

[0338] Data Cleansing

[0339] server

[0340] The server then performs data cleansing on the collected daily activity data. It detects outliers and missing data and corrects or removes them. This process uses statistical methods and heuristic rules. For example, extremely high heart rates and unnatural step counts are treated as outliers.

[0341] Input: Raw data stored in a database

[0342] Output: A cleansed, highly accurate dataset

[0343] Step 3:

[0344] Data analysis

[0345] server

[0346] The server uses the cleansed data to analyze the child's sleep rhythm and sleep onset trends. It uses machine learning algorithms (e.g., random forests, neural networks) to extract patterns and analyze trends. For example, it identifies patterns of decreased heart rate at certain times of the day or periods of reduced physical activity.

[0347] Input: Cleansed dataset

[0348] Output: Analysis results (child's sleep rhythm and tendency to fall asleep)

[0349] Step 4:

[0350] Calculating the optimal time to fall asleep

[0351] server

[0352] The server then calculates the optimal time to fall asleep for that day based on the analysis results. It makes the prediction by combining the average time to fall asleep obtained from past data with the activity data for that day. For example, if you exercise a lot that day, it will set an earlier time to fall asleep.

[0353] Input: Analysis results and activity data for the day

[0354] Output: Optimal sleep time

[0355] Step 5:

[0356] Timeline Generation

[0357] server

[0358] The server generates a timeline of preparation steps (e.g., dinner, bath, etc.) before falling asleep based on the optimal time to fall asleep. For example, if the time to fall asleep is 8:30 PM, it creates a schedule for dinner at 6:30 PM and bath time at 7:30 PM. Specifically, the server uses rule-based logic to build the timeline.

[0359] Input: Optimal time to fall asleep

[0360] Output: Generated timeline

[0361] Step 6:

[0362] Emotional engine regulation

[0363] server

[0364] The server uses an emotion engine to collect the child's facial expressions and voice data and analyze their emotions. Based on real-time data acquired through the camera and microphone, the server evaluates the child's emotional state, reflects this in the timeline, and adds relaxation activities as needed.

[0365] Input: Generated timeline and emotion data

[0366] Output: Adjusted timeline that takes emotions into account

[0367] Step 7:

[0368] notification

[0369] Terminal

[0370] The device (parent's smartphone) receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[0371] Input: Adjusted timeline

[0372] Output: Schedule and advice displayed on the smartphone app

[0373] Step 8:

[0374] feedback

[0375] User

[0376] The user (parent) checks the app's notifications, manages their child's life according to the suggested schedule, actually performs relaxation activities (e.g., reading aloud, playing music), and enters the results as feedback into the app.

[0377] Input: Implemented schedule and feedback

[0378] Output: Feedback data entered into the app

[0379] Step 9:

[0380] Processing Feedback

[0381] server

[0382] The server stores and analyzes user feedback in a database, and uses the feedback data to make future schedule suggestions and adjust the emotion engine.

[0383] Input: Feedback data

[0384] Output: Improved proposal and adjusted schedule

[0385] (Application example 2)

[0386] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0387] In recent years, there has been a surge in interest in children's sleep rhythms and emotional lifestyle management. However, existing systems only provide an appropriate timeline for sleep onset based on daily activity data, and are unable to respond to real-time emotional changes. This makes it difficult to respond appropriately to stress or discomfort felt at specific times, posing challenges to children's health management and maintaining a comfortable lifestyle.

[0388] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the child's daily activities, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for an emotion engine to collect data on the child's facial expressions and voice and recognize emotions, means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine, and means for notifying the user's terminal of the generated timeline. This makes it possible to manage the child's health and maintain a comfortable lifestyle by suggesting an optimal time to fall asleep while responding to emotional changes in real time.

[0389] "Means for collecting children's daily activity data" refers to devices or software that use activity trackers or life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.).

[0390] "Means for analyzing a child's sleep rhythm and sleep onset tendency based on collected data" refers to devices or programs that use collected daily activity data to analyze a child's individual sleep rhythm and sleep onset tendency through machine learning algorithms and statistical methods.

[0391] "Means for generating a timeline of preparations before falling asleep from the analysis results" refers to a device or program that determines the optimal time for a child to fall asleep based on the analyzed data and generates a schedule of the specific preparatory actions (e.g., meals, bathing, relaxation) required to reach that time.

[0392] "Means for the emotion engine to collect the child's facial expressions and voice data and recognize emotions" refers to devices or programs that collect the child's facial expressions and voice data in real time through a camera or microphone, and analyze this data to determine the child's emotional state.

[0393] The "means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine" refers to a device or program that combines a pre-sleep timeline that has been generated in advance with the analysis results of the emotion engine, and adds relaxation activities or other adjustments to the timeline as necessary.

[0394] "Means for notifying the user of the generated timeline" refers to a system or program for notifying the parent or user of the final adjusted timeline on their device, such as a smartphone or tablet.

[0395] The present invention relates to a system for suggesting an optimal time for a child to fall asleep. In particular, this embodiment shows a system that combines a child's daily activity data with real-time emotional data to generate an optimal timeline and notify a parent or user. As a novel application example, a system that suggests optimal work break times to maximize the work efficiency of robots in a factory is also considered.

[0396] System configuration:

[0397] 1. Data collection methods:

[0398] The server uses activity trackers and life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.) It also collects data from various sensors (vibration sensors, temperature sensors, operating time sensors, etc.) attached to robots in the factory.

[0399] 2. Data analysis methods:

[0400] The server analyzes the collected data to track the sleep rhythms and sleep onset patterns of the child and robot, as well as their work performance. This analysis uses Python-based machine learning algorithms (such as Scikit-learn and TensorFlow) to identify individual trends.

[0401] 3. Timeline generation method:

[0402] Based on the analysis results, the server calculates optimal times for falling asleep and resting, and generates specific preparation actions and schedules to achieve these times. The generated timeline includes preparation times before falling asleep (eating, bathing, relaxation, etc.) for children, and optimal work breaks and work schedules for robots.

[0403] 4. How to recognize emotions:

[0404] The emotion engine collects facial and voice data from the child and robot via the camera and microphone, and recognizes their emotions using facial recognition and voice analysis libraries (OpenCV, Google Cloud Speech-to-Text, etc.).

[0405] 5. Timeline fine-tuning methods:

[0406] The server fine-tunes the timeline based on the generated timeline and the analysis results of the emotion engine. For example, if a child feels stressed during a certain time period, it will add relaxation activities to that time period, or if the robot's task performance is declining, it will suggest a break.

[0407] 6. Means of notification:

[0408] The server then notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device, including specific schedules and advice.

[0409] Examples:

[0410] The automated transport robots in Factory A use vibration and temperature sensors to collect operational data, which is then analyzed using a Python-based machine learning algorithm. The resulting analysis results are used by a server to generate optimal work break times and schedules. The robots also monitor their surroundings using cameras and microphones, recognizing real-time emotional data and fine-tuning their timelines. The adjusted timelines are then sent to the factory's display system and the managers' smartphones.

[0411] Example prompt sentence:

[0412] "Factory A's automated transport robots collect operational data using vibration and temperature sensors. Based on this data, generate Python code that suggests optimal work schedules and break times. The code should also include an analysis section using a machine learning algorithm."

[0413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0414] Step 1:

[0415] Collect daily activity data of children and robots.

[0416] The server collects data from activity trackers, life log applications, and various sensors in the factory. This data includes the number of steps, exercise volume, heart rate, meal times, bath times, vibration, temperature, and sound. Input data is acquired from each sensor in real time and sent to the server, which then stores this data in temporary data storage.

[0417] Step 2:

[0418] The collected data is cleansed and stored in a database.

[0419] The server cleanses the temporarily stored data. This process corrects outliers and missing data to ensure data accuracy and consistency. Specifically, it filters out, for example, extremely high heart rates and abnormally long periods of inactivity. After the cleansing process is complete, the server stores the clean dataset in a secure database. The input data is the temporarily stored raw data, and the output data is the cleansed data.

[0420] Step 3:

[0421] The collected data is used to analyze the sleep rhythms and sleep onset tendencies of children and robots, as well as their work performance.

[0422] The server uses the cleansed data and applies machine learning algorithms (e.g., Scikit-learn or TensorFlow) to perform analysis. The input data is the cleansed activity data and sensor data, and the output data is the analysis results that indicate individual sleep rhythms and work performance. Specifically, it analyzes changes in heart rate patterns and exercise volume to identify the logic behind abnormalities.

[0423] Step 4:

[0424] The analysis results are used to generate a timeline for preparation before falling asleep, or a schedule for rest and work.

[0425] Based on the collected and analyzed data, the server generates a timeline that includes the optimal time for the child to fall asleep and the optimal time for the robot to rest. The input data is the analysis result, and the output data is a specific timeline schedule. For example, if the child falls asleep at 8:30 PM, a timeline is generated that includes dinner at 6:30 PM and bath time at 7:30 PM. Similarly, optimal rest times and work schedules are also calculated based on the robot's operating data.

[0426] Step 5:

[0427] The emotion engine collects facial and voice data from children and robots to recognize their emotions.

[0428] The server uses real-time facial and voice data collected through cameras and microphones and analyzes it using an emotion engine. The input data is the facial and voice data collected in real time, and the output data is the emotion analysis results. Specifically, it uses facial recognition software (such as OpenCV) and voice analysis libraries (such as Google Cloud Speech-to-Text) to determine the stress level and discomfort of children and robots.

[0429] Step 6:

[0430] Fine-tune the timeline based on the analysis results of the emotion engine.

[0431] The server incorporates the emotion engine's analysis results into the generated timeline and fine-tunes it as needed. For example, if a child feels stressed during a certain time period, it can add relaxation activities to that time period, or if a robot's work performance is declining, it can add rest periods. The input data are the emotion engine's analysis results and the existing timeline, and the output data is the fine-tuned timeline.

[0432] Step 7:

[0433] The final adjusted timeline is notified to the user's terminal.

[0434] The server notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device. The input data is the final adjusted timeline, and the output data is a schedule notification displayed on the user's device. Specifically, push notifications and alerts are sent to smartphone apps and display systems within the factory. This allows users to receive visual instructions and take appropriate action.

[0435] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0436] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0437] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0438] [Second embodiment]

[0439] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0440] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0441] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0442] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0443] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0444] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0445] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0446] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0447] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0448] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0449] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0450] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0451] MODE FOR CARRYING OUT THE INVENTION

[0452] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and an embodiment thereof will be described below.

[0453] System configuration

[0454] The system includes means for collecting data on a child's daily activities, means for analyzing the collected data, means for generating a timeline from the analysis results, and means for notifying the child of the generated timeline.

[0455] Specific examples of programs

[0456] 1. Data Collection

[0457] server

[0458] The server periodically collects children's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from activity trackers and smartphone apps.

[0459] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[0460] 2. Data Analysis

[0461] server

[0462] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[0463] As a specific example, data from the past few weeks is used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops).

[0464] 3. Timeline generation

[0465] server

[0466] Based on the analysis results, the server calculates the optimal time to fall asleep for that day.

[0467] Next, the system calculates backwards based on the optimal time to fall asleep and generates a timeline for preparations before falling asleep (eating, bathing, etc.).

[0468] For example, if the optimal time to fall asleep is 8:30 p.m., create a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[0469] 4. Notification

[0470] Terminal

[0471] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app.

[0472] For example, the app will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[0473] User

[0474] Parents can monitor their child's life by checking the app's notifications and following the suggested schedule.

[0475] Parents act as if they start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30.

[0476] As described above, the system works in conjunction with the server and devices to calculate the optimal time for a child to fall asleep and help parents prepare for sleep appropriately. This system allows parents to alleviate their children's sleep deprivation and ensure a healthy lifestyle.

[0477] The processing flow will be explained below.

[0478] Step 1:

[0479] User

[0480] The user (parent) launches the smartphone app and sets up a child's account by entering basic information such as the child's name, age, and gender.

[0481] Step 2:

[0482] Terminal

[0483] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[0484] Step 3:

[0485] server

[0486] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[0487] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[0488] Step 4:

[0489] server

[0490] The server uses machine learning algorithms to analyze the child's sleep rhythm and sleep onset tendency based on data from the past few weeks.

[0491] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[0492] Step 5:

[0493] server

[0494] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[0495] Step 6:

[0496] server

[0497] Based on the optimal time to fall asleep calculated by the server, a timeline of preparations before falling asleep (eating, bathing, etc.) is generated.

[0498] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[0499] Step 7:

[0500] server

[0501] The server pushes the generated timeline to the parent's smartphone.

[0502] Step 8:

[0503] Terminal

[0504] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[0505] For example, it will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[0506] Step 9:

[0507] User

[0508] Parents can check app notifications to help their children get ready for sleep.

[0509] Specifically, start preparing dinner at 18:30, feed dinner at 19:00, and give the baby a bath at 19:30.

[0510] This allows the system to help children maintain optimal sleep rhythms and allows parents to manage their children's lives at the appropriate time.

[0511] Example 1

[0512] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0513] It is known that lack of sleep in children has a negative impact on their growth and learning ability. However, it is difficult to find a sleep time that is appropriate for each child's daily rhythm. With conventional methods, parents often rely on experience and intuition to determine their child's sleep time, and there is a lack of means to derive the optimal sleep time based on scientific data analysis. Cleansing the collected data and appropriately setting notification timing are also challenges.

[0514] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0515] In this invention, the server includes means for collecting data on the child's daily activities, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for calculating an optimal sleep onset time from the analysis results and generating a timeline for preparations before falling asleep, means for notifying a user's terminal of the generated timeline, and means for sending a notification based on the timeline to encourage the user to prepare the child for sleep. This allows the server to suggest an optimal sleep onset time for each child based on scientific data analysis and to notify parents of the notification so that they can appropriately prepare for sleep.

[0516] - "Children's daily activity data" refers to data that indicates the movements and physical indicators of children in their daily lives, including the number of steps taken, amount of exercise, heart rate, meal times, bathing times, etc.

[0517] An "activity tracker" is a device used to measure and collect data on a child's physical activity, such as a smartwatch or fitness tracker.

[0518] A "life log application" is a software application for recording and managing various data about a child's daily life.

[0519] "Data cleansing" is the process of correcting outliers and missing data from a collected dataset to build an accurate dataset.

[0520] "Database" refers to a system for organizing and storing information, and for safely and efficiently storing and managing collected activity data.

[0521] "Sleep rhythm" refers to a child's daily sleep patterns and cycles, and usually indicates the tendency for sleep onset and wakefulness times over a certain period of time.

[0522] "Sleep tendency" indicates the tendency of a child to fall asleep easily under what conditions or circumstances.

[0523] The "timeline" calculates the optimal time to fall asleep and shows a specific schedule for making various preparations before falling asleep.

[0524] A "machine learning algorithm" is a method by which a computer learns patterns from data and makes predictions and classifications, and in this invention it is used to analyze sleep rhythms and sleep onset tendencies.

[0525] A "notification" is a message or alert that notifies a user of specific information, and includes push notifications from applications displayed on a device.

[0526] MODE FOR CARRYING OUT THE INVENTION

[0527] The present invention is a system for proposing an optimal time for a child to fall asleep, in which a server, a terminal, and a user play their respective roles, and is specifically implemented as follows.

[0528] System configuration

[0529] server

[0530] The server uses activity trackers (e.g., smartwatches or fitness trackers) and life log applications (e.g., health apps on smartphones) to collect data on the child's daily activities.

[0531] The server cleanses the collected data, correcting outliers and missing data to build an accurate dataset, improving data quality and increasing the reliability of analysis results.

[0532] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's sleep rhythm and sleep onset tendency, using Python libraries such as Scikit-learn and TensorFlow.

[0533] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then calculates backwards from the optimal time to fall asleep and generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner begins at 6:30 p.m. and bathing ends at 7:30 p.m.

[0534] Terminal

[0535] The parent's smartphone (device) receives push notifications sent from the server. The notifications include a timeline and specific advice for optimally preparing the child for sleep. For example, the app displays alerts such as "Start preparing dinner at 6:30 PM," "Dinner at 7:00 PM," and "Start preparing for bath time at 7:30 PM."

[0536] User

[0537] Parents can check the app's notifications and manage their children's lives according to the suggested schedule. For example, parents can start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. This will improve the quality of their children's sleep and ensure a healthy daily rhythm.

[0538] Specific examples

[0539] The specific analysis method involves extracting average sleep onset times and sleep patterns using data from the past few weeks. For example, a timeline can be generated by following the steps below.

[0540] Collecting exercise and heart rate data

[0541] Cleansing the data and storing it in the database

[0542] Analysis using machine learning algorithms

[0543] Calculating the optimal time to fall asleep

[0544] Creating a timeline for preparation before falling asleep

[0545] Push notifications to devices

[0546] Prompt Sentence Examples

[0547] Here are some examples of prompts to input to a generative AI model:

[0548] markdown

[0549] The system collects data on your child's daily activities and suggests the optimal time for them to fall asleep. It analyzes the collected data and calculates the optimal time for them to fall asleep for that day. For example, it generates a timeline like this:

[0550] 18:30 Start preparing dinner

[0551] 19:00 Dinner

[0552] 19:30 Start preparing for bathing

[0553] Sticking to this schedule will improve the quality of your child's sleep.

[0554] Specific timeline

[0555] Below is an example of a timeline generated by the system:

[0556] Dinner starts at 18:30

[0557] Bathing starts at 19:30

[0558] Using these prompts, the generative AI model can provide a specific timeline, allowing parents to find the optimal time for their child to fall asleep and make appropriate preparations.

[0559] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0560] Step 1:

[0561] The server collects data on children's daily activities. Specifically, it collects data using activity trackers (e.g., smartwatches and fitness trackers) and life log applications (e.g., smartphone health apps). As input, it receives data from each device, such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times. As output, it temporarily stores this data.

[0562] Step 2:

[0563] The server cleanses the collected data. Cleansing includes correcting outliers and missing data. For example, it identifies obviously abnormal or missing values ​​from the collected data and corrects or removes them in an appropriate way. The collected daily activity data is used as input. The output is a cleansed, accurate data set.

[0564] Step 3:

[0565] The server stores the cleansed data in a secure database. The database includes a means for efficiently storing and managing the acquired activity data. The cleansed data is used as input. The output is the data stored in the secure database.

[0566] Step 4:

[0567] The server analyzes the child's sleep rhythm and sleep onset tendency based on the collected daily activity data. A machine learning algorithm is used for the analysis. Specifically, Python's Scikit-learn and TensorFlow are used to extract the child's average sleep onset time and sleep onset pattern from each data point. The daily activity data stored in the database is used as input. The analysis results of the sleep rhythm and sleep onset tendency are obtained as output.

[0568] Step 5:

[0569] The server calculates the optimal time to fall asleep for that day based on the analysis results and generates a timeline for preparations before falling asleep. For example, if the optimal time to fall asleep is 8:30 PM, a timeline is created in which dinner begins at 6:30 PM and bathing ends at 7:30 PM. The analysis results are used as input, and a specific timeline is generated as output.

[0570] Step 6:

[0571] The server notifies the user's device of the generated timeline. The device may be a parent's smartphone. The server sends a push notification using a service such as Firebase Cloud Messaging (FCM). The generated timeline is used as input. The notification is sent to the device as output.

[0572] Step 7:

[0573] The parent (user) checks the notification on the smartphone (device) and manages the child's life according to the suggested schedule. For example, based on the device notification, the parent may start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. The timeline notification displayed on the device is used as input. The output is the execution of the child's life management.

[0574] By carrying out the above steps in sequence, it is possible to build a system that suggests the optimal time for a child to fall asleep and allows parents to make appropriate preparations.

[0575] (Application example 1)

[0576] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0577] Conventional systems that suggest optimal sleep times for children have problems with insufficient data collection and analysis, making it difficult to accurately grasp individual sleep rhythms and sleep onset tendencies. Furthermore, if notifications of preparation schedules before bedtime are not effective, it is difficult for parents to take appropriate action, preventing the maintenance of a healthy lifestyle rhythm for their children. Therefore, there was a need for a system that could provide more accurate notifications that were easy for users to understand.

[0578] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0579] In this invention, the server includes means for collecting daily activity data of a child, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for notifying a user's device of the generated timeline, means for sending a push notification to the user's device, and means for analyzing data using a machine learning algorithm. This makes it possible to accurately analyze a child's individual sleep rhythm and effectively notify parents of the optimal time to fall asleep and the preparation schedule before that time.

[0580] "Children's daily activity data" refers to data on activities that children perform in their daily lives, and includes information such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times.

[0581] "Collection methods" refers to devices or software used to collect data on a child's daily activities, such as activity trackers or life logging applications.

[0582] "Means for analysis" refers to devices or software that analyze a child's sleep rhythm and tendency to fall asleep based on the collected data, and may specifically use machine learning algorithms.

[0583] "Means for generating a timeline" refers to a device or software for creating a preparation schedule before falling asleep based on the analysis results.

[0584] "Means for notifying" refers to devices or software for notifying the user's device of the generated timeline, and includes push notifications.

[0585] "User's terminal" refers to a device such as a smartphone or tablet used by a user.

[0586] "Means for sending push notifications" refers to devices or software that send messages in real time from a server to a user's device, such as a smartphone.

[0587] "Means for analyzing data using machine learning algorithms" refers to devices or software that use artificial intelligence technology to accurately predict and analyze a child's individual sleep rhythm and sleep onset tendency based on collected data.

[0588] The present invention relates to a system for suggesting an optimal time for a child to fall asleep, and an embodiment thereof will be described in detail below.

[0589] System configuration

[0590] Data collection

[0591] Activity trackers and lifelogging applications are used to collect data on children's daily activities, which periodically transmit data such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times to a server. The server stores the collected data in a secure database and performs data cleansing. Data cleansing involves correcting outliers and missing data to build an accurate dataset.

[0592] Data analysis

[0593] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency. Specifically, machine learning frameworks such as TensorFlow are used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops) from data from the past few weeks.

[0594] Timeline Generation

[0595] Based on the analysis results, the server calculates the optimal time to fall asleep for that day. Then, by working backwards from the optimal time, it generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[0596] notification

[0597] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app. For example, the app can display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30." Parents can check the app's notifications and manage their children's lives according to the suggested schedule. This allows parents to prevent their children from getting enough sleep and ensure a healthy lifestyle.

[0598] Examples and prompts

[0599] For example, based on data recorded by an activity tracker, the following schedule could be sent to a parent's smartphone.

[0600] Example prompt:

[0601] "Analyze your child's sleep rhythm and create a timeline for optimal sleep onset."

[0602] This system allows parents to receive specific instructions in real time, such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30," enabling them to effectively manage their children's daily rhythms.

[0603] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0604] Step 1:

[0605] The server collects children's daily activity data from activity trackers and lifelogging applications. The collected data includes the number of steps, exercise volume, heart rate, meal times, bath time, etc. This data is sent to the server via the network. The input is the raw data from the activity trackers and lifelogging applications, which is then stored in a secure database.

[0606] Step 2:

[0607] The server cleanses the collected daily activity data. As part of the cleansing process, it corrects outliers and missing data to build an accurate dataset. Specifically, it performs operations such as deleting values ​​outside the data range and filling in missing values ​​with the average value. The input is the raw data collected in step 1, and the output is a cleansed, accurate dataset.

[0608] Step 3:

[0609] The server then uses machine learning algorithms to analyze the cleansed data. Specifically, it uses frameworks such as TensorFlow to analyze the child's sleep rhythm and sleep onset tendency. Data from the past few weeks is used as input to extract the child's average sleep onset time and sleep onset pattern. The output is the analysis results of sleep onset tendency and sleep onset pattern.

[0610] Step 4:

[0611] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then works backwards from this optimal time to generate a preparation schedule before falling asleep. For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner starts at 6:30 p.m. and bathing finishes at 7:30 p.m. The input is the analysis results obtained in step 3, and the output is a specific preparation schedule.

[0612] Step 5:

[0613] The server pushes the generated preparation schedule to the user's device. Specifically, it sends notifications to the parent's smartphone with content such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30." The input is the preparation schedule generated in step 4, and the output is the notification content displayed on the user's device.

[0614] Step 6:

[0615] Users can check notifications on their smartphones and manage their children's lives according to the suggested schedule. For example, parents can ensure their children fall asleep at the optimal time by starting dinner preparation at 18:30, feeding them at 19:00, and starting bathing at 19:30. The input is the notification content on the device, and the output is the child's healthy lifestyle rhythm.

[0616] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0617] MODE FOR CARRYING OUT THE INVENTION

[0618] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and embodiments thereof will be described below. In particular, by combining it with an emotion engine that recognizes the user's emotions, further effects can be provided.

[0619] System configuration

[0620] The system includes a means for collecting data on a child's daily activities, a means for analyzing the collected data, a means for generating a timeline from the analysis results, a means for notifying the user of the generated timeline, and an emotion engine for recognizing the user's emotions.

[0621] Specific examples of programs

[0622] 1. Data Collection

[0623] server

[0624] The server periodically collects the child's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app.

[0625] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[0626] 2. Data Analysis

[0627] server

[0628] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[0629] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[0630] 3. Calculating the optimal time to fall asleep

[0631] server

[0632] Based on the analysis results, the server calculates the optimal time to fall asleep for that day by combining the average time to fall asleep obtained from past data with the activity data for that day.

[0633] 4. Timeline generation

[0634] server

[0635] The server generates a timeline of preparations before falling asleep (eating, bathing, etc.) based on the optimal time to fall asleep.

[0636] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[0637] 5. Emotional Engine Adjustment

[0638] server

[0639] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[0640] The server takes into account the emotion engine's analysis and fine-tunes the timeline, for example, if a child feels stressed during a certain time period, it will add relaxation activities during that time.

[0641] 6. Notification

[0642] Terminal

[0643] The parent's smartphone receives push notifications from the server and displays the schedule and advice on the app.

[0644] Specifically, alerts will be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[0645] 7. Feedback

[0646] User

[0647] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[0648] Parents engage in relaxation activities with their children (e.g., reading aloud, playing music).

[0649] Parents enter feedback into the app, reporting any problems encountered during implementation and their child's emotional state.

[0650] 8. Processing Feedback

[0651] server

[0652] The server receives feedback from the parents and stores it in a database.

[0653] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[0654] In this way, the system maintains an optimal sleep rhythm for children through collaboration between the server, device, and user, and enables flexible responses to emotional situations through the emotion engine, thereby realizing health management for children and the establishment of a comfortable daily rhythm.

[0655] The processing flow will be explained below.

[0656] Step 1:

[0657] User

[0658] Parents launch the smartphone app and set up their child's account by entering basic information such as their child's name, age, and gender.

[0659] Step 2:

[0660] Terminal

[0661] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[0662] Step 3:

[0663] server

[0664] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[0665] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[0666] Step 4:

[0667] server

[0668] The server analyzes the child's sleep rhythm and sleep onset patterns based on data from the past few weeks, and machine learning algorithms identify patterns of decreased heart rate and decreased physical activity at certain times of the day.

[0669] Step 5:

[0670] server

[0671] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[0672] Step 6:

[0673] server

[0674] The server generates a timeline for preparations before falling asleep (e.g., meals and bathing) based on the optimal time to fall asleep. For example, if the patient falls asleep at 8:30 PM, the server creates a schedule for dinner at 6:30 PM and bathing at 7:30 PM.

[0675] Step 7:

[0676] server

[0677] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[0678] The timeline is fine-tuned based on the emotion engine's analysis: for example, if a child is feeling stressed, add relaxation activities during that time.

[0679] Step 8:

[0680] server

[0681] The server pushes the generated timeline to the parent's smartphone.

[0682] Step 9:

[0683] Terminal

[0684] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[0685] For example, alerts could be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[0686] Step 10:

[0687] User

[0688] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[0689] For example, start preparing dinner at 18:30, feed dinner at 19:00, and bathe at 19:30. Additionally, if your child is feeling stressed, engage in relaxation activities (e.g., reading aloud, playing music).

[0690] Step 11:

[0691] User

[0692] Parents enter feedback into the app, reporting ongoing issues and their child's emotional state.

[0693] Step 12:

[0694] server

[0695] The server receives the feedback from the parents and stores it in a database.

[0696] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[0697] This allows the system to help children maintain optimal sleep rhythms and parents to manage their children's lives at the appropriate time.The emotion engine also enables flexible responses according to emotional situations.

[0698] Example 2

[0699] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0700] Current child sleep schedule management systems do not adequately consider a child's individual sleep rhythm or emotional state. Furthermore, there are many challenges in analyzing collected data and reflecting it in the timeline. As a result, parents struggle to find the optimal time for their child to fall asleep, which can have a negative impact on the child's health. The present invention aims to flexibly adjust the optimal sleep time and timeline based on the child's daily activity data and emotional data, and provide parents with accurate notifications.

[0701] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting daily activity data of a child, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep from the analysis results, means for fine-tuning the generated timeline taking emotions into consideration, means for notifying the user's terminal of the generated timeline, and means for collecting and processing feedback from the user. This makes it possible to propose a flexible schedule according to the individual situation of each child, and ensure the optimal time for falling asleep.

[0702] "Children's daily activity data" is information about the activities that children perform in their daily lives, including the number of steps, amount of exercise, heart rate, meal times, bath times, and the like.

[0703] "Data cleansing" is the process of correcting outliers and missing data in collected data to build an accurate and usable dataset.

[0704] A "database" is a system for storing and managing collected data, allowing necessary information to be retrieved efficiently.

[0705] "Sleep rhythm" refers to a child's sleep-wake pattern over a period of time, a cycle based on their natural biological clock.

[0706] "Sleep onset tendency" refers to the pattern or tendency of when and under what circumstances a child falls asleep.

[0707] A "timeline" is a timetable that indicates the best times to perform certain events or activities, including preparation steps before falling asleep.

[0708] The "emotion engine" is a system that recognizes emotions from a child's facial expressions and voice data, allowing it to analyze their emotional state.

[0709] "Fine-tuning" means flexibly modifying the generated timeline based on new information such as the analysis results of the emotion engine.

[0710] A "terminal" is a device that receives notifications and information from a server and displays them to the user, and includes smartphones, tablets, etc.

[0711] "Feedback" refers to opinions and impressions provided by users, as well as information about problems and emotional states during execution.

[0712] A "machine learning algorithm" is a computational method that automatically learns specific patterns and trends from data and makes predictions and classifications for new data.

[0713] The present invention provides a system for proposing an optimal sleep time for a child, and an embodiment thereof will be described in detail below. The system collects and analyzes a child's daily activity data to generate an optimal sleep time and a timeline for achieving this. It also includes a means for appropriately adjusting the timeline, taking into account the child's emotional state. This system promotes health management and optimization of the child's daily rhythm.

[0714] System configuration

[0715] The system consists of the following main components:

[0716] 1. Means of collecting data on children's daily activities

[0717] 2. How to cleanse and store the collected data in a database

[0718] 3. A means of analyzing children's sleep rhythms and sleep onset tendencies based on collected data

[0719] 4. A method for generating a timeline of preparations before falling asleep from the analysis results

[0720] 5. A means to collect emotional data and fine-tune the timeline through an emotional engine

[0721] 6. A method for notifying the user of the generated timeline

[0722] 7. How to collect and process user feedback

[0723] Data Collection and Cleansing

[0724] server

[0725] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and lifelogging applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath times, etc. The collected data is stored in a secure database. A data cleansing process corrects outliers and missing data to build an accurate dataset.

[0726] Data analysis and calculation of optimal sleep onset time

[0727] server

[0728] The server analyzes the collected daily activity data using machine learning algorithms (e.g., random forests and neural networks). This analysis allows the server to understand the child's sleep rhythm and sleep onset tendency. For example, it identifies patterns of decreased heart rate and reduced physical activity at certain times of the day. Based on this, the server calculates the optimal time for the child to fall asleep.

[0729] Creating and adjusting timelines

[0730] server

[0731] The server generates a timeline based on the optimal time to fall asleep, including preparation steps before falling asleep (e.g., dinner, bath, etc.). For example, to fall asleep at 8:30 p.m., it creates a schedule such as dinner at 6:30 p.m. and bath time at 7:30 p.m. Furthermore, it analyzes emotional data collected by the emotion engine (e.g., obtained using a camera or microphone) and fine-tunes the timeline. If a child feels stressed in the evening, it adds relaxation activities (e.g., listening to music) to that time period.

[0732] Schedule notifications and feedback

[0733] Terminal

[0734] The parent's smartphone receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath time at 19:30," and "Relaxation time at 20:00." Users can enter feedback through the app to report any problems encountered during execution and their child's emotional state.

[0735] server

[0736] The server stores and analyzes parent feedback in a database. This feedback data is used to improve future schedule suggestions and adjust the emotion engine. For example, the effectiveness of relaxation activities can be evaluated to improve the accuracy of future suggestions.

[0737] Examples of concrete examples and prompts

[0738] For example, the following prompt sentence is input to the generative AI model:

[0739] "My child has been waking up late recently. Can you suggest an optimal time for him to fall asleep?"

[0740] "Tell me about relaxation activities to help reduce my child's stress levels."

[0741] This system allows the server, device, and user to work together to maintain a child's optimal sleep rhythm and respond flexibly to their emotional state, thereby helping to manage a child's health and establishing a comfortable daily rhythm.

[0742] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0743] Step 1:

[0744] Data collection

[0745] server

[0746] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and life log applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath time, etc. Specifically, the server obtains data from each device through an API and stores it in a secure database.

[0747] Input: Raw data from activity trackers and life logging applications

[0748] Output: Daily activity data stored in a secure database

[0749] Step 2:

[0750] Data Cleansing

[0751] server

[0752] The server then performs data cleansing on the collected daily activity data. It detects outliers and missing data and corrects or removes them. This process uses statistical methods and heuristic rules. For example, extremely high heart rates and unnatural step counts are treated as outliers.

[0753] Input: Raw data stored in a database

[0754] Output: A cleansed, highly accurate dataset

[0755] Step 3:

[0756] Data analysis

[0757] server

[0758] The server uses the cleansed data to analyze the child's sleep rhythm and sleep onset trends. It uses machine learning algorithms (e.g., random forests, neural networks) to extract patterns and analyze trends. For example, it identifies patterns of decreased heart rate at certain times of the day or periods of reduced physical activity.

[0759] Input: Cleansed dataset

[0760] Output: Analysis results (child's sleep rhythm and tendency to fall asleep)

[0761] Step 4:

[0762] Calculating the optimal time to fall asleep

[0763] server

[0764] The server then calculates the optimal time to fall asleep for that day based on the analysis results. It makes the prediction by combining the average time to fall asleep obtained from past data with the activity data for that day. For example, if you exercise a lot that day, it will set an earlier time to fall asleep.

[0765] Input: Analysis results and activity data for the day

[0766] Output: Optimal sleep time

[0767] Step 5:

[0768] Timeline Generation

[0769] server

[0770] The server generates a timeline of preparation steps (e.g., dinner, bath, etc.) before falling asleep based on the optimal time to fall asleep. For example, if the time to fall asleep is 8:30 PM, it creates a schedule for dinner at 6:30 PM and bath time at 7:30 PM. Specifically, the server uses rule-based logic to build the timeline.

[0771] Input: Optimal time to fall asleep

[0772] Output: Generated timeline

[0773] Step 6:

[0774] Emotional engine regulation

[0775] server

[0776] The server uses an emotion engine to collect the child's facial expressions and voice data and analyze their emotions. Based on real-time data acquired through the camera and microphone, the server evaluates the child's emotional state, reflects this in the timeline, and adds relaxation activities as needed.

[0777] Input: Generated timeline and emotion data

[0778] Output: Adjusted timeline that takes emotions into account

[0779] Step 7:

[0780] notification

[0781] Terminal

[0782] The device (parent's smartphone) receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[0783] Input: Adjusted timeline

[0784] Output: Schedule and advice displayed on the smartphone app

[0785] Step 8:

[0786] feedback

[0787] User

[0788] The user (parent) checks the app's notifications, manages their child's life according to the suggested schedule, actually performs relaxation activities (e.g., reading aloud, playing music), and enters the results as feedback into the app.

[0789] Input: Implemented schedule and feedback

[0790] Output: Feedback data entered into the app

[0791] Step 9:

[0792] Processing Feedback

[0793] server

[0794] The server stores and analyzes user feedback in a database, and uses the feedback data to make future schedule suggestions and adjust the emotion engine.

[0795] Input: Feedback data

[0796] Output: Improved proposal and adjusted schedule

[0797] (Application example 2)

[0798] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0799] In recent years, there has been a surge in interest in children's sleep rhythms and emotional lifestyle management. However, existing systems only provide an appropriate timeline for sleep onset based on daily activity data, and are unable to respond to real-time emotional changes. This makes it difficult to respond appropriately to stress or discomfort felt at specific times, posing challenges to children's health management and maintaining a comfortable lifestyle.

[0800] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the child's daily activities, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for an emotion engine to collect data on the child's facial expressions and voice and recognize emotions, means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine, and means for notifying the user's terminal of the generated timeline. This makes it possible to manage the child's health and maintain a comfortable lifestyle by suggesting an optimal time to fall asleep while responding to emotional changes in real time.

[0801] "Means for collecting children's daily activity data" refers to devices or software that use activity trackers or life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.).

[0802] "Means for analyzing a child's sleep rhythm and sleep onset tendency based on collected data" refers to devices or programs that use collected daily activity data to analyze a child's individual sleep rhythm and sleep onset tendency through machine learning algorithms and statistical methods.

[0803] "Means for generating a timeline of preparations before falling asleep from the analysis results" refers to a device or program that determines the optimal time for a child to fall asleep based on the analyzed data and generates a schedule of the specific preparatory actions (e.g., meals, bathing, relaxation) required to reach that time.

[0804] "Means for the emotion engine to collect the child's facial expressions and voice data and recognize emotions" refers to devices or programs that collect the child's facial expressions and voice data in real time through a camera or microphone, and analyze this data to determine the child's emotional state.

[0805] The "means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine" refers to a device or program that combines a pre-sleep timeline that has been generated in advance with the analysis results of the emotion engine, and adds relaxation activities or other adjustments to the timeline as necessary.

[0806] "Means for notifying the user of the generated timeline" refers to a system or program for notifying the parent or user of the final adjusted timeline on their device, such as a smartphone or tablet.

[0807] The present invention relates to a system for suggesting an optimal time for a child to fall asleep. In particular, this embodiment shows a system that combines a child's daily activity data with real-time emotional data to generate an optimal timeline and notify a parent or user. As a novel application example, a system that suggests optimal work break times to maximize the work efficiency of robots in a factory is also considered.

[0808] System configuration:

[0809] 1. Data collection methods:

[0810] The server uses activity trackers and life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.) It also collects data from various sensors (vibration sensors, temperature sensors, operating time sensors, etc.) attached to robots in the factory.

[0811] 2. Data analysis methods:

[0812] The server analyzes the collected data to track the sleep rhythms and sleep onset patterns of the child and robot, as well as their work performance. This analysis uses Python-based machine learning algorithms (such as Scikit-learn and TensorFlow) to identify individual trends.

[0813] 3. Timeline generation method:

[0814] Based on the analysis results, the server calculates optimal times for falling asleep and resting, and generates specific preparation actions and schedules to achieve these times. The generated timeline includes preparation times before falling asleep (eating, bathing, relaxation, etc.) for children, and optimal work breaks and work schedules for robots.

[0815] 4. How to recognize emotions:

[0816] The emotion engine collects facial and voice data from the child and robot via the camera and microphone, and recognizes their emotions using facial recognition and voice analysis libraries (OpenCV, Google Cloud Speech-to-Text, etc.).

[0817] 5. Timeline fine-tuning methods:

[0818] The server fine-tunes the timeline based on the generated timeline and the analysis results of the emotion engine. For example, if a child feels stressed during a certain time period, it will add relaxation activities to that time period, or if the robot's task performance is declining, it will suggest a break.

[0819] 6. Means of notification:

[0820] The server then notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device, including specific schedules and advice.

[0821] Examples:

[0822] The automated transport robots in Factory A use vibration and temperature sensors to collect operational data, which is then analyzed using a Python-based machine learning algorithm. The resulting analysis results are used by a server to generate optimal work break times and schedules. The robots also monitor their surroundings using cameras and microphones, recognizing real-time emotional data and fine-tuning their timelines. The adjusted timelines are then sent to the factory's display system and the managers' smartphones.

[0823] Example prompt sentence:

[0824] "Factory A's automated transport robots collect operational data using vibration and temperature sensors. Based on this data, generate Python code that suggests optimal work schedules and break times. The code should also include an analysis section using a machine learning algorithm."

[0825] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0826] Step 1:

[0827] Collect daily activity data of children and robots.

[0828] The server collects data from activity trackers, life log applications, and various sensors in the factory. This data includes the number of steps, exercise volume, heart rate, meal times, bath times, vibration, temperature, and sound. Input data is acquired from each sensor in real time and sent to the server, which then stores this data in temporary data storage.

[0829] Step 2:

[0830] The collected data is cleansed and stored in a database.

[0831] The server cleanses the temporarily stored data. This process corrects outliers and missing data to ensure data accuracy and consistency. Specifically, it filters out, for example, extremely high heart rates and abnormally long periods of inactivity. After the cleansing process is complete, the server stores the clean dataset in a secure database. The input data is the temporarily stored raw data, and the output data is the cleansed data.

[0832] Step 3:

[0833] The collected data is used to analyze the sleep rhythms and sleep onset tendencies of children and robots, as well as their work performance.

[0834] The server uses the cleansed data and applies machine learning algorithms (e.g., Scikit-learn or TensorFlow) to perform analysis. The input data is the cleansed activity data and sensor data, and the output data is the analysis results that indicate individual sleep rhythms and work performance. Specifically, it analyzes changes in heart rate patterns and exercise volume to identify the logic behind abnormalities.

[0835] Step 4:

[0836] The analysis results are used to generate a timeline for preparation before falling asleep, or a schedule for rest and work.

[0837] Based on the collected and analyzed data, the server generates a timeline that includes the optimal time for the child to fall asleep and the optimal time for the robot to rest. The input data is the analysis result, and the output data is a specific timeline schedule. For example, if the child falls asleep at 8:30 PM, a timeline is generated that includes dinner at 6:30 PM and bath time at 7:30 PM. Similarly, optimal rest times and work schedules are also calculated based on the robot's operating data.

[0838] Step 5:

[0839] The emotion engine collects facial and voice data from children and robots to recognize their emotions.

[0840] The server uses real-time facial and voice data collected through cameras and microphones and analyzes it using an emotion engine. The input data is the facial and voice data collected in real time, and the output data is the emotion analysis results. Specifically, it uses facial recognition software (such as OpenCV) and voice analysis libraries (such as Google Cloud Speech-to-Text) to determine the stress level and discomfort of children and robots.

[0841] Step 6:

[0842] Fine-tune the timeline based on the analysis results of the emotion engine.

[0843] The server incorporates the emotion engine's analysis results into the generated timeline and fine-tunes it as needed. For example, if a child feels stressed during a certain time period, it can add relaxation activities to that time period, or if a robot's work performance is declining, it can add rest periods. The input data are the emotion engine's analysis results and the existing timeline, and the output data is the fine-tuned timeline.

[0844] Step 7:

[0845] The final adjusted timeline is notified to the user's terminal.

[0846] The server notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device. The input data is the final adjusted timeline, and the output data is a schedule notification displayed on the user's device. Specifically, push notifications and alerts are sent to smartphone apps and display systems within the factory. This allows users to receive visual instructions and take appropriate action.

[0847] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0848] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0849] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0850] [Third embodiment]

[0851] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0852] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0853] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0854] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0855] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0856] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0857] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0858] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0859] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0860] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0861] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0862] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0863] MODE FOR CARRYING OUT THE INVENTION

[0864] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and an embodiment thereof will be described below.

[0865] System configuration

[0866] The system includes means for collecting data on a child's daily activities, means for analyzing the collected data, means for generating a timeline from the analysis results, and means for notifying the child of the generated timeline.

[0867] Specific examples of programs

[0868] 1. Data Collection

[0869] server

[0870] The server periodically collects children's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from activity trackers and smartphone apps.

[0871] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[0872] 2. Data Analysis

[0873] server

[0874] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[0875] As a specific example, data from the past few weeks is used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops).

[0876] 3. Timeline generation

[0877] server

[0878] Based on the analysis results, the server calculates the optimal time to fall asleep for that day.

[0879] Next, the system calculates backwards based on the optimal time to fall asleep and generates a timeline for preparations before falling asleep (eating, bathing, etc.).

[0880] For example, if the optimal time to fall asleep is 8:30 p.m., create a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[0881] 4. Notification

[0882] Terminal

[0883] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app.

[0884] For example, the app will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[0885] User

[0886] Parents can monitor their child's life by checking the app's notifications and following the suggested schedule.

[0887] Parents act as if they start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30.

[0888] As described above, the system works in conjunction with the server and devices to calculate the optimal time for a child to fall asleep and help parents prepare for sleep appropriately. This system allows parents to alleviate their children's sleep deprivation and ensure a healthy lifestyle.

[0889] The processing flow will be explained below.

[0890] Step 1:

[0891] User

[0892] The user (parent) launches the smartphone app and sets up a child's account by entering basic information such as the child's name, age, and gender.

[0893] Step 2:

[0894] Terminal

[0895] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[0896] Step 3:

[0897] server

[0898] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[0899] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[0900] Step 4:

[0901] server

[0902] The server uses machine learning algorithms to analyze the child's sleep rhythm and sleep onset tendency based on data from the past few weeks.

[0903] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[0904] Step 5:

[0905] server

[0906] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[0907] Step 6:

[0908] server

[0909] Based on the optimal time to fall asleep calculated by the server, a timeline of preparations before falling asleep (eating, bathing, etc.) is generated.

[0910] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[0911] Step 7:

[0912] server

[0913] The server pushes the generated timeline to the parent's smartphone.

[0914] Step 8:

[0915] Terminal

[0916] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[0917] For example, it will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[0918] Step 9:

[0919] User

[0920] Parents can check app notifications to help their children get ready for sleep.

[0921] Specifically, start preparing dinner at 18:30, feed dinner at 19:00, and give the baby a bath at 19:30.

[0922] This allows the system to help children maintain optimal sleep rhythms and allows parents to manage their children's lives at the appropriate time.

[0923] Example 1

[0924] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0925] It is known that lack of sleep in children has a negative impact on their growth and learning ability. However, it is difficult to find a sleep time that is appropriate for each child's daily rhythm. With conventional methods, parents often rely on experience and intuition to determine their child's sleep time, and there is a lack of means to derive the optimal sleep time based on scientific data analysis. Cleansing the collected data and appropriately setting notification timing are also challenges.

[0926] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0927] In this invention, the server includes means for collecting data on the child's daily activities, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for calculating an optimal sleep onset time from the analysis results and generating a timeline for preparations before falling asleep, means for notifying a user's terminal of the generated timeline, and means for sending a notification based on the timeline to encourage the user to prepare the child for sleep. This allows the server to suggest an optimal sleep onset time for each child based on scientific data analysis and to notify parents of the notification so that they can appropriately prepare for sleep.

[0928] - "Children's daily activity data" refers to data that indicates the movements and physical indicators of children in their daily lives, including the number of steps taken, amount of exercise, heart rate, meal times, bathing times, etc.

[0929] An "activity tracker" is a device used to measure and collect data on a child's physical activity, such as a smartwatch or fitness tracker.

[0930] A "life log application" is a software application for recording and managing various data about a child's daily life.

[0931] "Data cleansing" is the process of correcting outliers and missing data from a collected dataset to build an accurate dataset.

[0932] "Database" refers to a system for organizing and storing information, and for safely and efficiently storing and managing collected activity data.

[0933] "Sleep rhythm" refers to a child's daily sleep patterns and cycles, and usually indicates the tendency for sleep onset and wakefulness times over a certain period of time.

[0934] "Sleep tendency" indicates the tendency of a child to fall asleep easily under what conditions or circumstances.

[0935] The "timeline" calculates the optimal time to fall asleep and shows a specific schedule for making various preparations before falling asleep.

[0936] A "machine learning algorithm" is a method by which a computer learns patterns from data and makes predictions and classifications, and in this invention it is used to analyze sleep rhythms and sleep onset tendencies.

[0937] A "notification" is a message or alert that notifies a user of specific information, and includes push notifications from applications displayed on a device.

[0938] MODE FOR CARRYING OUT THE INVENTION

[0939] The present invention is a system for proposing an optimal time for a child to fall asleep, in which a server, a terminal, and a user play their respective roles, and is specifically implemented as follows.

[0940] System configuration

[0941] server

[0942] The server uses activity trackers (e.g., smartwatches or fitness trackers) and life log applications (e.g., health apps on smartphones) to collect data on the child's daily activities.

[0943] The server cleanses the collected data, correcting outliers and missing data to build an accurate dataset, improving data quality and increasing the reliability of analysis results.

[0944] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's sleep rhythm and sleep onset tendency, using Python libraries such as Scikit-learn and TensorFlow.

[0945] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then calculates backwards from the optimal time to fall asleep and generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner begins at 6:30 p.m. and bathing ends at 7:30 p.m.

[0946] Terminal

[0947] The parent's smartphone (device) receives push notifications sent from the server. The notifications include a timeline and specific advice for optimally preparing the child for sleep. For example, the app displays alerts such as "Start preparing dinner at 6:30 PM," "Dinner at 7:00 PM," and "Start preparing for bath time at 7:30 PM."

[0948] User

[0949] Parents can check the app's notifications and manage their children's lives according to the suggested schedule. For example, parents can start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. This will improve the quality of their children's sleep and ensure a healthy daily rhythm.

[0950] Specific examples

[0951] The specific analysis method involves extracting average sleep onset times and sleep patterns using data from the past few weeks. For example, a timeline can be generated by following the steps below.

[0952] Collecting exercise and heart rate data

[0953] Cleansing the data and storing it in the database

[0954] Analysis using machine learning algorithms

[0955] Calculating the optimal time to fall asleep

[0956] Creating a timeline for preparation before falling asleep

[0957] Push notifications to devices

[0958] Prompt Sentence Examples

[0959] Here are some examples of prompts to input to a generative AI model:

[0960] markdown

[0961] The system collects data on your child's daily activities and suggests the optimal time for them to fall asleep. It analyzes the collected data and calculates the optimal time for them to fall asleep for that day. For example, it generates a timeline like this:

[0962] 18:30 Start preparing dinner

[0963] 19:00 Dinner

[0964] 19:30 Start preparing for bathing

[0965] Sticking to this schedule will improve the quality of your child's sleep.

[0966] Specific timeline

[0967] Below is an example of a timeline generated by the system:

[0968] Dinner starts at 18:30

[0969] Bathing starts at 19:30

[0970] Using these prompts, the generative AI model can provide a specific timeline, allowing parents to find the optimal time for their child to fall asleep and make appropriate preparations.

[0971] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0972] Step 1:

[0973] The server collects data on children's daily activities. Specifically, it collects data using activity trackers (e.g., smartwatches and fitness trackers) and life log applications (e.g., smartphone health apps). As input, it receives data from each device, such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times. As output, it temporarily stores this data.

[0974] Step 2:

[0975] The server cleanses the collected data. Cleansing includes correcting outliers and missing data. For example, it identifies obviously abnormal or missing values ​​from the collected data and corrects or removes them in an appropriate way. The collected daily activity data is used as input. The output is a cleansed, accurate data set.

[0976] Step 3:

[0977] The server stores the cleansed data in a secure database. The database includes a means for efficiently storing and managing the acquired activity data. The cleansed data is used as input. The output is the data stored in the secure database.

[0978] Step 4:

[0979] The server analyzes the child's sleep rhythm and sleep onset tendency based on the collected daily activity data. A machine learning algorithm is used for the analysis. Specifically, Python's Scikit-learn and TensorFlow are used to extract the child's average sleep onset time and sleep onset pattern from each data point. The daily activity data stored in the database is used as input. The analysis results of the sleep rhythm and sleep onset tendency are obtained as output.

[0980] Step 5:

[0981] The server calculates the optimal time to fall asleep for that day based on the analysis results and generates a timeline for preparations before falling asleep. For example, if the optimal time to fall asleep is 8:30 PM, a timeline is created in which dinner begins at 6:30 PM and bathing ends at 7:30 PM. The analysis results are used as input, and a specific timeline is generated as output.

[0982] Step 6:

[0983] The server notifies the user's device of the generated timeline. The device may be a parent's smartphone. The server sends a push notification using a service such as Firebase Cloud Messaging (FCM). The generated timeline is used as input. The notification is sent to the device as output.

[0984] Step 7:

[0985] The parent (user) checks the notification on the smartphone (device) and manages the child's life according to the suggested schedule. For example, based on the device notification, the parent may start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. The timeline notification displayed on the device is used as input. The output is the execution of the child's life management.

[0986] By carrying out the above steps in sequence, it is possible to build a system that suggests the optimal time for a child to fall asleep and allows parents to make appropriate preparations.

[0987] (Application example 1)

[0988] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0989] Conventional systems that suggest optimal sleep times for children have problems with insufficient data collection and analysis, making it difficult to accurately grasp individual sleep rhythms and sleep onset tendencies. Furthermore, if notifications of preparation schedules before bedtime are not effective, it is difficult for parents to take appropriate action, preventing the maintenance of a healthy lifestyle rhythm for their children. Therefore, there was a need for a system that could provide more accurate notifications that were easy for users to understand.

[0990] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0991] In this invention, the server includes means for collecting daily activity data of a child, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for notifying a user's device of the generated timeline, means for sending a push notification to the user's device, and means for analyzing data using a machine learning algorithm. This makes it possible to accurately analyze a child's individual sleep rhythm and effectively notify parents of the optimal time to fall asleep and the preparation schedule before that time.

[0992] "Children's daily activity data" refers to data on activities that children perform in their daily lives, and includes information such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times.

[0993] "Collection methods" refers to devices or software used to collect data on a child's daily activities, such as activity trackers or life logging applications.

[0994] "Means for analysis" refers to devices or software that analyze a child's sleep rhythm and tendency to fall asleep based on the collected data, and may specifically use machine learning algorithms.

[0995] "Means for generating a timeline" refers to a device or software for creating a preparation schedule before falling asleep based on the analysis results.

[0996] "Means for notifying" refers to devices or software for notifying the user's device of the generated timeline, and includes push notifications.

[0997] "User's terminal" refers to a device such as a smartphone or tablet used by a user.

[0998] "Means for sending push notifications" refers to devices or software that send messages in real time from a server to a user's device, such as a smartphone.

[0999] "Means for analyzing data using machine learning algorithms" refers to devices or software that use artificial intelligence technology to accurately predict and analyze a child's individual sleep rhythm and sleep onset tendency based on collected data.

[1000] The present invention relates to a system for suggesting an optimal time for a child to fall asleep, and an embodiment thereof will be described in detail below.

[1001] System configuration

[1002] Data collection

[1003] Activity trackers and lifelogging applications are used to collect data on children's daily activities, which periodically transmit data such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times to a server. The server stores the collected data in a secure database and performs data cleansing. Data cleansing involves correcting outliers and missing data to build an accurate dataset.

[1004] Data analysis

[1005] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency. Specifically, machine learning frameworks such as TensorFlow are used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops) from data from the past few weeks.

[1006] Timeline Generation

[1007] Based on the analysis results, the server calculates the optimal time to fall asleep for that day. Then, by working backwards from the optimal time, it generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[1008] notification

[1009] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app. For example, the app can display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30." Parents can check the app's notifications and manage their children's lives according to the suggested schedule. This allows parents to prevent their children from getting enough sleep and ensure a healthy lifestyle.

[1010] Examples and prompts

[1011] For example, based on data recorded by an activity tracker, the following schedule could be sent to a parent's smartphone.

[1012] Example prompt:

[1013] "Analyze your child's sleep rhythm and create a timeline for optimal sleep onset."

[1014] This system allows parents to receive specific instructions in real time, such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30," enabling them to effectively manage their children's daily rhythms.

[1015] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1016] Step 1:

[1017] The server collects children's daily activity data from activity trackers and lifelogging applications. The collected data includes the number of steps, exercise volume, heart rate, meal times, bath time, etc. This data is sent to the server via the network. The input is the raw data from the activity trackers and lifelogging applications, which is then stored in a secure database.

[1018] Step 2:

[1019] The server cleanses the collected daily activity data. As part of the cleansing process, it corrects outliers and missing data to build an accurate dataset. Specifically, it performs operations such as deleting values ​​outside the data range and filling in missing values ​​with the average value. The input is the raw data collected in step 1, and the output is a cleansed, accurate dataset.

[1020] Step 3:

[1021] The server then uses machine learning algorithms to analyze the cleansed data. Specifically, it uses frameworks such as TensorFlow to analyze the child's sleep rhythm and sleep onset tendency. Data from the past few weeks is used as input to extract the child's average sleep onset time and sleep onset pattern. The output is the analysis results of sleep onset tendency and sleep onset pattern.

[1022] Step 4:

[1023] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then works backwards from this optimal time to generate a preparation schedule before falling asleep. For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner starts at 6:30 p.m. and bathing finishes at 7:30 p.m. The input is the analysis results obtained in step 3, and the output is a specific preparation schedule.

[1024] Step 5:

[1025] The server pushes the generated preparation schedule to the user's device. Specifically, it sends notifications to the parent's smartphone with content such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30." The input is the preparation schedule generated in step 4, and the output is the notification content displayed on the user's device.

[1026] Step 6:

[1027] Users can check notifications on their smartphones and manage their children's lives according to the suggested schedule. For example, parents can ensure their children fall asleep at the optimal time by starting dinner preparation at 18:30, feeding them at 19:00, and starting bathing at 19:30. The input is the notification content on the device, and the output is the child's healthy lifestyle rhythm.

[1028] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1029] MODE FOR CARRYING OUT THE INVENTION

[1030] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and embodiments thereof will be described below. In particular, by combining it with an emotion engine that recognizes the user's emotions, further effects can be provided.

[1031] System configuration

[1032] The system includes a means for collecting data on a child's daily activities, a means for analyzing the collected data, a means for generating a timeline from the analysis results, a means for notifying the user of the generated timeline, and an emotion engine for recognizing the user's emotions.

[1033] Specific examples of programs

[1034] 1. Data Collection

[1035] server

[1036] The server periodically collects the child's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app.

[1037] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[1038] 2. Data Analysis

[1039] server

[1040] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[1041] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[1042] 3. Calculating the optimal time to fall asleep

[1043] server

[1044] Based on the analysis results, the server calculates the optimal time to fall asleep for that day by combining the average time to fall asleep obtained from past data with the activity data for that day.

[1045] 4. Timeline generation

[1046] server

[1047] The server generates a timeline of preparations before falling asleep (eating, bathing, etc.) based on the optimal time to fall asleep.

[1048] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[1049] 5. Emotional Engine Adjustment

[1050] server

[1051] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[1052] The server takes into account the emotion engine's analysis and fine-tunes the timeline, for example, if a child feels stressed during a certain time period, it will add relaxation activities during that time.

[1053] 6. Notification

[1054] Terminal

[1055] The parent's smartphone receives push notifications from the server and displays the schedule and advice on the app.

[1056] Specifically, alerts will be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[1057] 7. Feedback

[1058] User

[1059] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[1060] Parents engage in relaxation activities with their children (e.g., reading aloud, playing music).

[1061] Parents enter feedback into the app, reporting any problems encountered during implementation and their child's emotional state.

[1062] 8. Processing Feedback

[1063] server

[1064] The server receives feedback from the parents and stores it in a database.

[1065] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[1066] In this way, the system maintains an optimal sleep rhythm for children through collaboration between the server, device, and user, and enables flexible responses to emotional situations through the emotion engine, thereby realizing health management for children and the establishment of a comfortable daily rhythm.

[1067] The processing flow will be explained below.

[1068] Step 1:

[1069] User

[1070] Parents launch the smartphone app and set up their child's account by entering basic information such as their child's name, age, and gender.

[1071] Step 2:

[1072] Terminal

[1073] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[1074] Step 3:

[1075] server

[1076] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[1077] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[1078] Step 4:

[1079] server

[1080] The server analyzes the child's sleep rhythm and sleep onset patterns based on data from the past few weeks, and machine learning algorithms identify patterns of decreased heart rate and decreased physical activity at certain times of the day.

[1081] Step 5:

[1082] server

[1083] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[1084] Step 6:

[1085] server

[1086] The server generates a timeline for preparations before falling asleep (e.g., meals and bathing) based on the optimal time to fall asleep. For example, if the patient falls asleep at 8:30 PM, the server creates a schedule for dinner at 6:30 PM and bathing at 7:30 PM.

[1087] Step 7:

[1088] server

[1089] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[1090] The timeline is fine-tuned based on the emotion engine's analysis: for example, if a child is feeling stressed, add relaxation activities during that time.

[1091] Step 8:

[1092] server

[1093] The server pushes the generated timeline to the parent's smartphone.

[1094] Step 9:

[1095] Terminal

[1096] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[1097] For example, alerts could be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[1098] Step 10:

[1099] User

[1100] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[1101] For example, start preparing dinner at 18:30, feed dinner at 19:00, and bathe at 19:30. Additionally, if your child is feeling stressed, engage in relaxation activities (e.g., reading aloud, playing music).

[1102] Step 11:

[1103] User

[1104] Parents enter feedback into the app, reporting ongoing issues and their child's emotional state.

[1105] Step 12:

[1106] server

[1107] The server receives the feedback from the parents and stores it in a database.

[1108] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[1109] This allows the system to help children maintain optimal sleep rhythms and parents to manage their children's lives at the appropriate time.The emotion engine also enables flexible responses according to emotional situations.

[1110] Example 2

[1111] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1112] Current child sleep schedule management systems do not adequately consider a child's individual sleep rhythm or emotional state. Furthermore, there are many challenges in analyzing collected data and reflecting it in the timeline. As a result, parents struggle to find the optimal time for their child to fall asleep, which can have a negative impact on the child's health. The present invention aims to flexibly adjust the optimal sleep time and timeline based on the child's daily activity data and emotional data, and provide parents with accurate notifications.

[1113] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting daily activity data of a child, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep from the analysis results, means for fine-tuning the generated timeline taking emotions into consideration, means for notifying the user's terminal of the generated timeline, and means for collecting and processing feedback from the user. This makes it possible to propose a flexible schedule according to the individual situation of each child, and ensure the optimal time for falling asleep.

[1114] "Children's daily activity data" is information about the activities that children perform in their daily lives, including the number of steps, amount of exercise, heart rate, meal times, bath times, and the like.

[1115] "Data cleansing" is the process of correcting outliers and missing data in collected data to build an accurate and usable dataset.

[1116] A "database" is a system for storing and managing collected data, allowing necessary information to be retrieved efficiently.

[1117] "Sleep rhythm" refers to a child's sleep-wake pattern over a period of time, a cycle based on their natural biological clock.

[1118] "Sleep onset tendency" refers to the pattern or tendency of when and under what circumstances a child falls asleep.

[1119] A "timeline" is a timetable that indicates the best times to perform certain events or activities, including preparation steps before falling asleep.

[1120] The "emotion engine" is a system that recognizes emotions from a child's facial expressions and voice data, allowing it to analyze their emotional state.

[1121] "Fine-tuning" means flexibly modifying the generated timeline based on new information such as the analysis results of the emotion engine.

[1122] A "terminal" is a device that receives notifications and information from a server and displays them to the user, and includes smartphones, tablets, etc.

[1123] "Feedback" refers to opinions and impressions provided by users, as well as information about problems and emotional states during execution.

[1124] A "machine learning algorithm" is a computational method that automatically learns specific patterns and trends from data and makes predictions and classifications for new data.

[1125] The present invention provides a system for proposing an optimal sleep time for a child, and an embodiment thereof will be described in detail below. The system collects and analyzes a child's daily activity data to generate an optimal sleep time and a timeline for achieving this. It also includes a means for appropriately adjusting the timeline, taking into account the child's emotional state. This system promotes health management and optimization of the child's daily rhythm.

[1126] System configuration

[1127] The system consists of the following main components:

[1128] 1. Means of collecting data on children's daily activities

[1129] 2. How to cleanse and store the collected data in a database

[1130] 3. A means of analyzing children's sleep rhythms and sleep onset tendencies based on collected data

[1131] 4. A method for generating a timeline of preparations before falling asleep from the analysis results

[1132] 5. A means to collect emotional data and fine-tune the timeline through an emotional engine

[1133] 6. A method for notifying the user of the generated timeline

[1134] 7. How to collect and process user feedback

[1135] Data Collection and Cleansing

[1136] server

[1137] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and lifelogging applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath times, etc. The collected data is stored in a secure database. A data cleansing process corrects outliers and missing data to build an accurate dataset.

[1138] Data analysis and calculation of optimal sleep onset time

[1139] server

[1140] The server analyzes the collected daily activity data using machine learning algorithms (e.g., random forests and neural networks). This analysis allows the server to understand the child's sleep rhythm and sleep onset tendency. For example, it identifies patterns of decreased heart rate and reduced physical activity at certain times of the day. Based on this, the server calculates the optimal time for the child to fall asleep.

[1141] Creating and adjusting timelines

[1142] server

[1143] The server generates a timeline based on the optimal time to fall asleep, including preparation steps before falling asleep (e.g., dinner, bath, etc.). For example, to fall asleep at 8:30 p.m., it creates a schedule such as dinner at 6:30 p.m. and bath time at 7:30 p.m. Furthermore, it analyzes emotional data collected by the emotion engine (e.g., obtained using a camera or microphone) and fine-tunes the timeline. If a child feels stressed in the evening, it adds relaxation activities (e.g., listening to music) to that time period.

[1144] Schedule notifications and feedback

[1145] Terminal

[1146] The parent's smartphone receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath time at 19:30," and "Relaxation time at 20:00." Users can enter feedback through the app to report any problems encountered during execution and their child's emotional state.

[1147] server

[1148] The server stores and analyzes parent feedback in a database. This feedback data is used to improve future schedule suggestions and adjust the emotion engine. For example, the effectiveness of relaxation activities can be evaluated to improve the accuracy of future suggestions.

[1149] Examples of concrete examples and prompts

[1150] For example, the following prompt sentence is input to the generative AI model:

[1151] "My child has been waking up late recently. Can you suggest an optimal time for him to fall asleep?"

[1152] "Tell me about relaxation activities to help reduce my child's stress levels."

[1153] This system allows the server, device, and user to work together to maintain a child's optimal sleep rhythm and respond flexibly to their emotional state, thereby helping to manage a child's health and establishing a comfortable daily rhythm.

[1154] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1155] Step 1:

[1156] Data collection

[1157] server

[1158] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and life log applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath time, etc. Specifically, the server obtains data from each device through an API and stores it in a secure database.

[1159] Input: Raw data from activity trackers and life logging applications

[1160] Output: Daily activity data stored in a secure database

[1161] Step 2:

[1162] Data Cleansing

[1163] server

[1164] The server then performs data cleansing on the collected daily activity data. It detects outliers and missing data and corrects or removes them. This process uses statistical methods and heuristic rules. For example, extremely high heart rates and unnatural step counts are treated as outliers.

[1165] Input: Raw data stored in a database

[1166] Output: A cleansed, highly accurate dataset

[1167] Step 3:

[1168] Data analysis

[1169] server

[1170] The server uses the cleansed data to analyze the child's sleep rhythm and sleep onset trends. It uses machine learning algorithms (e.g., random forests, neural networks) to extract patterns and analyze trends. For example, it identifies patterns of decreased heart rate at certain times of the day or periods of reduced physical activity.

[1171] Input: Cleansed dataset

[1172] Output: Analysis results (child's sleep rhythm and tendency to fall asleep)

[1173] Step 4:

[1174] Calculating the optimal time to fall asleep

[1175] server

[1176] The server then calculates the optimal time to fall asleep for that day based on the analysis results. It makes the prediction by combining the average time to fall asleep obtained from past data with the activity data for that day. For example, if you exercise a lot that day, it will set an earlier time to fall asleep.

[1177] Input: Analysis results and activity data for the day

[1178] Output: Optimal sleep time

[1179] Step 5:

[1180] Timeline Generation

[1181] server

[1182] The server generates a timeline of preparation steps (e.g., dinner, bath, etc.) before falling asleep based on the optimal time to fall asleep. For example, if the time to fall asleep is 8:30 PM, it creates a schedule for dinner at 6:30 PM and bath time at 7:30 PM. Specifically, the server uses rule-based logic to build the timeline.

[1183] Input: Optimal time to fall asleep

[1184] Output: Generated timeline

[1185] Step 6:

[1186] Emotional engine regulation

[1187] server

[1188] The server uses an emotion engine to collect the child's facial expressions and voice data and analyze their emotions. Based on real-time data acquired through the camera and microphone, the server evaluates the child's emotional state, reflects this in the timeline, and adds relaxation activities as needed.

[1189] Input: Generated timeline and emotion data

[1190] Output: Adjusted timeline that takes emotions into account

[1191] Step 7:

[1192] notification

[1193] Terminal

[1194] The device (parent's smartphone) receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[1195] Input: Adjusted timeline

[1196] Output: Schedule and advice displayed on the smartphone app

[1197] Step 8:

[1198] feedback

[1199] User

[1200] The user (parent) checks the app's notifications, manages their child's life according to the suggested schedule, actually performs relaxation activities (e.g., reading aloud, playing music), and enters the results as feedback into the app.

[1201] Input: Implemented schedule and feedback

[1202] Output: Feedback data entered into the app

[1203] Step 9:

[1204] Processing Feedback

[1205] server

[1206] The server stores and analyzes user feedback in a database, and uses the feedback data to make future schedule suggestions and adjust the emotion engine.

[1207] Input: Feedback data

[1208] Output: Improved proposal and adjusted schedule

[1209] (Application example 2)

[1210] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1211] In recent years, there has been a surge in interest in children's sleep rhythms and emotional lifestyle management. However, existing systems only provide an appropriate timeline for sleep onset based on daily activity data, and are unable to respond to real-time emotional changes. This makes it difficult to respond appropriately to stress or discomfort felt at specific times, posing challenges to children's health management and maintaining a comfortable lifestyle.

[1212] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the child's daily activities, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for an emotion engine to collect data on the child's facial expressions and voice and recognize emotions, means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine, and means for notifying the user's terminal of the generated timeline. This makes it possible to manage the child's health and maintain a comfortable lifestyle by suggesting an optimal time to fall asleep while responding to emotional changes in real time.

[1213] "Means for collecting children's daily activity data" refers to devices or software that use activity trackers or life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.).

[1214] "Means for analyzing a child's sleep rhythm and sleep onset tendency based on collected data" refers to devices or programs that use collected daily activity data to analyze a child's individual sleep rhythm and sleep onset tendency through machine learning algorithms and statistical methods.

[1215] "Means for generating a timeline of preparations before falling asleep from the analysis results" refers to a device or program that determines the optimal time for a child to fall asleep based on the analyzed data and generates a schedule of the specific preparatory actions (e.g., meals, bathing, relaxation) required to reach that time.

[1216] "Means for the emotion engine to collect the child's facial expressions and voice data and recognize emotions" refers to devices or programs that collect the child's facial expressions and voice data in real time through a camera or microphone, and analyze this data to determine the child's emotional state.

[1217] The "means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine" refers to a device or program that combines a pre-sleep timeline that has been generated in advance with the analysis results of the emotion engine, and adds relaxation activities or other adjustments to the timeline as necessary.

[1218] "Means for notifying the user of the generated timeline" refers to a system or program for notifying the parent or user of the final adjusted timeline on their device, such as a smartphone or tablet.

[1219] The present invention relates to a system for suggesting an optimal time for a child to fall asleep. In particular, this embodiment shows a system that combines a child's daily activity data with real-time emotional data to generate an optimal timeline and notify a parent or user. As a novel application example, a system that suggests optimal work break times to maximize the work efficiency of robots in a factory is also considered.

[1220] System configuration:

[1221] 1. Data collection methods:

[1222] The server uses activity trackers and life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.) It also collects data from various sensors (vibration sensors, temperature sensors, operating time sensors, etc.) attached to robots in the factory.

[1223] 2. Data analysis methods:

[1224] The server analyzes the collected data to track the sleep rhythms and sleep onset patterns of the child and robot, as well as their work performance. This analysis uses Python-based machine learning algorithms (such as Scikit-learn and TensorFlow) to identify individual trends.

[1225] 3. Timeline generation method:

[1226] Based on the analysis results, the server calculates optimal times for falling asleep and resting, and generates specific preparation actions and schedules to achieve these times. The generated timeline includes preparation times before falling asleep (eating, bathing, relaxation, etc.) for children, and optimal work breaks and work schedules for robots.

[1227] 4. How to recognize emotions:

[1228] The emotion engine collects facial and voice data from the child and robot via the camera and microphone, and recognizes their emotions using facial recognition and voice analysis libraries (OpenCV, Google Cloud Speech-to-Text, etc.).

[1229] 5. Timeline fine-tuning methods:

[1230] The server fine-tunes the timeline based on the generated timeline and the analysis results of the emotion engine. For example, if a child feels stressed during a certain time period, it will add relaxation activities to that time period, or if the robot's task performance is declining, it will suggest a break.

[1231] 6. Means of notification:

[1232] The server then notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device, including specific schedules and advice.

[1233] Examples:

[1234] The automated transport robots in Factory A use vibration and temperature sensors to collect operational data, which is then analyzed using a Python-based machine learning algorithm. The resulting analysis results are used by a server to generate optimal work break times and schedules. The robots also monitor their surroundings using cameras and microphones, recognizing real-time emotional data and fine-tuning their timelines. The adjusted timelines are then sent to the factory's display system and the managers' smartphones.

[1235] Example prompt sentence:

[1236] "Factory A's automated transport robots collect operational data using vibration and temperature sensors. Based on this data, generate Python code that suggests optimal work schedules and break times. The code should also include an analysis section using a machine learning algorithm."

[1237] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1238] Step 1:

[1239] Collect daily activity data of children and robots.

[1240] The server collects data from activity trackers, life log applications, and various sensors in the factory. This data includes the number of steps, exercise volume, heart rate, meal times, bath times, vibration, temperature, and sound. Input data is acquired from each sensor in real time and sent to the server, which then stores this data in temporary data storage.

[1241] Step 2:

[1242] The collected data is cleansed and stored in a database.

[1243] The server cleanses the temporarily stored data. This process corrects outliers and missing data to ensure data accuracy and consistency. Specifically, it filters out, for example, extremely high heart rates and abnormally long periods of inactivity. After the cleansing process is complete, the server stores the clean dataset in a secure database. The input data is the temporarily stored raw data, and the output data is the cleansed data.

[1244] Step 3:

[1245] The collected data is used to analyze the sleep rhythms and sleep onset tendencies of children and robots, as well as their work performance.

[1246] The server uses the cleansed data and applies machine learning algorithms (e.g., Scikit-learn or TensorFlow) to perform analysis. The input data is the cleansed activity data and sensor data, and the output data is the analysis results that indicate individual sleep rhythms and work performance. Specifically, it analyzes changes in heart rate patterns and exercise volume to identify the logic behind abnormalities.

[1247] Step 4:

[1248] The analysis results are used to generate a timeline for preparation before falling asleep, or a schedule for rest and work.

[1249] Based on the collected and analyzed data, the server generates a timeline that includes the optimal time for the child to fall asleep and the optimal time for the robot to rest. The input data is the analysis result, and the output data is a specific timeline schedule. For example, if the child falls asleep at 8:30 PM, a timeline is generated that includes dinner at 6:30 PM and bath time at 7:30 PM. Similarly, optimal rest times and work schedules are also calculated based on the robot's operating data.

[1250] Step 5:

[1251] The emotion engine collects facial and voice data from children and robots to recognize their emotions.

[1252] The server uses real-time facial and voice data collected through cameras and microphones and analyzes it using an emotion engine. The input data is the facial and voice data collected in real time, and the output data is the emotion analysis results. Specifically, it uses facial recognition software (such as OpenCV) and voice analysis libraries (such as Google Cloud Speech-to-Text) to determine the stress level and discomfort of children and robots.

[1253] Step 6:

[1254] Fine-tune the timeline based on the analysis results of the emotion engine.

[1255] The server incorporates the emotion engine's analysis results into the generated timeline and fine-tunes it as needed. For example, if a child feels stressed during a certain time period, it can add relaxation activities to that time period, or if a robot's work performance is declining, it can add rest periods. The input data are the emotion engine's analysis results and the existing timeline, and the output data is the fine-tuned timeline.

[1256] Step 7:

[1257] The final adjusted timeline is notified to the user's terminal.

[1258] The server notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device. The input data is the final adjusted timeline, and the output data is a schedule notification displayed on the user's device. Specifically, push notifications and alerts are sent to smartphone apps and display systems within the factory. This allows users to receive visual instructions and take appropriate action.

[1259] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1260] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1261] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1262] [Fourth embodiment]

[1263] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1264] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1265] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1266] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1267] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1268] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1269] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1270] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1271] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1272] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1273] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1274] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1275] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1276] MODE FOR CARRYING OUT THE INVENTION

[1277] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and an embodiment thereof will be described below.

[1278] System configuration

[1279] The system includes means for collecting data on a child's daily activities, means for analyzing the collected data, means for generating a timeline from the analysis results, and means for notifying the child of the generated timeline.

[1280] Specific examples of programs

[1281] 1. Data Collection

[1282] server

[1283] The server periodically collects children's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from activity trackers and smartphone apps.

[1284] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[1285] 2. Data Analysis

[1286] server

[1287] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[1288] As a specific example, data from the past few weeks is used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops).

[1289] 3. Timeline generation

[1290] server

[1291] Based on the analysis results, the server calculates the optimal time to fall asleep for that day.

[1292] Next, the system calculates backwards based on the optimal time to fall asleep and generates a timeline for preparations before falling asleep (eating, bathing, etc.).

[1293] For example, if the optimal time to fall asleep is 8:30 p.m., create a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[1294] 4. Notification

[1295] Terminal

[1296] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app.

[1297] For example, the app will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[1298] User

[1299] Parents can monitor their child's life by checking the app's notifications and following the suggested schedule.

[1300] Parents act as if they start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30.

[1301] As described above, the system works in conjunction with the server and devices to calculate the optimal time for a child to fall asleep and help parents prepare for sleep appropriately. This system allows parents to alleviate their children's sleep deprivation and ensure a healthy lifestyle.

[1302] The processing flow will be explained below.

[1303] Step 1:

[1304] User

[1305] The user (parent) launches the smartphone app and sets up a child's account by entering basic information such as the child's name, age, and gender.

[1306] Step 2:

[1307] Terminal

[1308] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[1309] Step 3:

[1310] server

[1311] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[1312] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[1313] Step 4:

[1314] server

[1315] The server uses machine learning algorithms to analyze the child's sleep rhythm and sleep onset tendency based on data from the past few weeks.

[1316] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[1317] Step 5:

[1318] server

[1319] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[1320] Step 6:

[1321] server

[1322] Based on the optimal time to fall asleep calculated by the server, a timeline of preparations before falling asleep (eating, bathing, etc.) is generated.

[1323] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[1324] Step 7:

[1325] server

[1326] The server pushes the generated timeline to the parent's smartphone.

[1327] Step 8:

[1328] Terminal

[1329] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[1330] For example, it will display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30."

[1331] Step 9:

[1332] User

[1333] Parents can check app notifications to help their children get ready for sleep.

[1334] Specifically, start preparing dinner at 18:30, feed dinner at 19:00, and give the baby a bath at 19:30.

[1335] This allows the system to help children maintain optimal sleep rhythms and allows parents to manage their children's lives at the appropriate time.

[1336] Example 1

[1337] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1338] It is known that lack of sleep in children has a negative impact on their growth and learning ability. However, it is difficult to find a sleep time that is appropriate for each child's daily rhythm. With conventional methods, parents often rely on experience and intuition to determine their child's sleep time, and there is a lack of means to derive the optimal sleep time based on scientific data analysis. Cleansing the collected data and appropriately setting notification timing are also challenges.

[1339] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1340] In this invention, the server includes means for collecting data on the child's daily activities, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for calculating an optimal sleep onset time from the analysis results and generating a timeline for preparations before falling asleep, means for notifying a user's terminal of the generated timeline, and means for sending a notification based on the timeline to encourage the user to prepare the child for sleep. This allows the server to suggest an optimal sleep onset time for each child based on scientific data analysis and to notify parents of the notification so that they can appropriately prepare for sleep.

[1341] - "Children's daily activity data" refers to data that indicates the movements and physical indicators of children in their daily lives, including the number of steps taken, amount of exercise, heart rate, meal times, bathing times, etc.

[1342] An "activity tracker" is a device used to measure and collect data on a child's physical activity, such as a smartwatch or fitness tracker.

[1343] A "life log application" is a software application for recording and managing various data about a child's daily life.

[1344] "Data cleansing" is the process of correcting outliers and missing data from a collected dataset to build an accurate dataset.

[1345] "Database" refers to a system for organizing and storing information, and for safely and efficiently storing and managing collected activity data.

[1346] "Sleep rhythm" refers to a child's daily sleep patterns and cycles, and usually indicates the tendency for sleep onset and wakefulness times over a certain period of time.

[1347] "Sleep tendency" indicates the tendency of a child to fall asleep easily under what conditions or circumstances.

[1348] The "timeline" calculates the optimal time to fall asleep and shows a specific schedule for making various preparations before falling asleep.

[1349] A "machine learning algorithm" is a method by which a computer learns patterns from data and makes predictions and classifications, and in this invention it is used to analyze sleep rhythms and sleep onset tendencies.

[1350] A "notification" is a message or alert that notifies a user of specific information, and includes push notifications from applications displayed on a device.

[1351] MODE FOR CARRYING OUT THE INVENTION

[1352] The present invention is a system for proposing an optimal time for a child to fall asleep, in which a server, a terminal, and a user play their respective roles, and is specifically implemented as follows.

[1353] System configuration

[1354] server

[1355] The server uses activity trackers (e.g., smartwatches or fitness trackers) and life log applications (e.g., health apps on smartphones) to collect data on the child's daily activities.

[1356] The server cleanses the collected data, correcting outliers and missing data to build an accurate dataset, improving data quality and increasing the reliability of analysis results.

[1357] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's sleep rhythm and sleep onset tendency, using Python libraries such as Scikit-learn and TensorFlow.

[1358] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then calculates backwards from the optimal time to fall asleep and generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner begins at 6:30 p.m. and bathing ends at 7:30 p.m.

[1359] Terminal

[1360] The parent's smartphone (device) receives push notifications sent from the server. The notifications include a timeline and specific advice for optimally preparing the child for sleep. For example, the app displays alerts such as "Start preparing dinner at 6:30 PM," "Dinner at 7:00 PM," and "Start preparing for bath time at 7:30 PM."

[1361] User

[1362] Parents can check the app's notifications and manage their children's lives according to the suggested schedule. For example, parents can start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. This will improve the quality of their children's sleep and ensure a healthy daily rhythm.

[1363] Specific examples

[1364] The specific analysis method involves extracting average sleep onset times and sleep patterns using data from the past few weeks. For example, a timeline can be generated by following the steps below.

[1365] Collecting exercise and heart rate data

[1366] Cleansing the data and storing it in the database

[1367] Analysis using machine learning algorithms

[1368] Calculating the optimal time to fall asleep

[1369] Creating a timeline for preparation before falling asleep

[1370] Push notifications to devices

[1371] Prompt Sentence Examples

[1372] Here are some examples of prompts to input to a generative AI model:

[1373] markdown

[1374] The system collects data on your child's daily activities and suggests the optimal time for them to fall asleep. It analyzes the collected data and calculates the optimal time for them to fall asleep for that day. For example, it generates a timeline like this:

[1375] 18:30 Start preparing dinner

[1376] 19:00 Dinner

[1377] 19:30 Start preparing for bathing

[1378] Sticking to this schedule will improve the quality of your child's sleep.

[1379] Specific timeline

[1380] Below is an example of a timeline generated by the system:

[1381] Dinner starts at 18:30

[1382] Bathing starts at 19:30

[1383] Using these prompts, the generative AI model can provide a specific timeline, allowing parents to find the optimal time for their child to fall asleep and make appropriate preparations.

[1384] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1385] Step 1:

[1386] The server collects data on children's daily activities. Specifically, it collects data using activity trackers (e.g., smartwatches and fitness trackers) and life log applications (e.g., smartphone health apps). As input, it receives data from each device, such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times. As output, it temporarily stores this data.

[1387] Step 2:

[1388] The server cleanses the collected data. Cleansing includes correcting outliers and missing data. For example, it identifies obviously abnormal or missing values ​​from the collected data and corrects or removes them in an appropriate way. The collected daily activity data is used as input. The output is a cleansed, accurate data set.

[1389] Step 3:

[1390] The server stores the cleansed data in a secure database. The database includes a means for efficiently storing and managing the acquired activity data. The cleansed data is used as input. The output is the data stored in the secure database.

[1391] Step 4:

[1392] The server analyzes the child's sleep rhythm and sleep onset tendency based on the collected daily activity data. A machine learning algorithm is used for the analysis. Specifically, Python's Scikit-learn and TensorFlow are used to extract the child's average sleep onset time and sleep onset pattern from each data point. The daily activity data stored in the database is used as input. The analysis results of the sleep rhythm and sleep onset tendency are obtained as output.

[1393] Step 5:

[1394] The server calculates the optimal time to fall asleep for that day based on the analysis results and generates a timeline for preparations before falling asleep. For example, if the optimal time to fall asleep is 8:30 PM, a timeline is created in which dinner begins at 6:30 PM and bathing ends at 7:30 PM. The analysis results are used as input, and a specific timeline is generated as output.

[1395] Step 6:

[1396] The server notifies the user's device of the generated timeline. The device may be a parent's smartphone. The server sends a push notification using a service such as Firebase Cloud Messaging (FCM). The generated timeline is used as input. The notification is sent to the device as output.

[1397] Step 7:

[1398] The parent (user) checks the notification on the smartphone (device) and manages the child's life according to the suggested schedule. For example, based on the device notification, the parent may start preparing dinner at 18:30, feed dinner at 19:00, and start bathing at 19:30. The timeline notification displayed on the device is used as input. The output is the execution of the child's life management.

[1399] By carrying out the above steps in sequence, it is possible to build a system that suggests the optimal time for a child to fall asleep and allows parents to make appropriate preparations.

[1400] (Application example 1)

[1401] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1402] Conventional systems that suggest optimal sleep times for children have problems with insufficient data collection and analysis, making it difficult to accurately grasp individual sleep rhythms and sleep onset tendencies. Furthermore, if notifications of preparation schedules before bedtime are not effective, it is difficult for parents to take appropriate action, preventing the maintenance of a healthy lifestyle rhythm for their children. Therefore, there was a need for a system that could provide more accurate notifications that were easy for users to understand.

[1403] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1404] In this invention, the server includes means for collecting daily activity data of a child, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for notifying a user's device of the generated timeline, means for sending a push notification to the user's device, and means for analyzing data using a machine learning algorithm. This makes it possible to accurately analyze a child's individual sleep rhythm and effectively notify parents of the optimal time to fall asleep and the preparation schedule before that time.

[1405] "Children's daily activity data" refers to data on activities that children perform in their daily lives, and includes information such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times.

[1406] "Collection methods" refers to devices or software used to collect data on a child's daily activities, such as activity trackers or life logging applications.

[1407] "Means for analysis" refers to devices or software that analyze a child's sleep rhythm and tendency to fall asleep based on the collected data, and may specifically use machine learning algorithms.

[1408] "Means for generating a timeline" refers to a device or software for creating a preparation schedule before falling asleep based on the analysis results.

[1409] "Means for notifying" refers to devices or software for notifying the user's device of the generated timeline, and includes push notifications.

[1410] "User's terminal" refers to a device such as a smartphone or tablet used by a user.

[1411] "Means for sending push notifications" refers to devices or software that send messages in real time from a server to a user's device, such as a smartphone.

[1412] "Means for analyzing data using machine learning algorithms" refers to devices or software that use artificial intelligence technology to accurately predict and analyze a child's individual sleep rhythm and sleep onset tendency based on collected data.

[1413] The present invention relates to a system for suggesting an optimal time for a child to fall asleep, and an embodiment thereof will be described in detail below.

[1414] System configuration

[1415] Data collection

[1416] Activity trackers and lifelogging applications are used to collect data on children's daily activities, which periodically transmit data such as the number of steps taken, amount of exercise, heart rate, meal times, and bath times to a server. The server stores the collected data in a secure database and performs data cleansing. Data cleansing involves correcting outliers and missing data to build an accurate dataset.

[1417] Data analysis

[1418] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency. Specifically, machine learning frameworks such as TensorFlow are used to extract average sleep onset times and sleep onset patterns (for example, specific amounts of exercise or times when heart rate drops) from data from the past few weeks.

[1419] Timeline Generation

[1420] Based on the analysis results, the server calculates the optimal time to fall asleep for that day. Then, by working backwards from the optimal time, it generates a timeline for preparations before falling asleep (e.g., eating and bathing). For example, if the optimal time to fall asleep is 8:30 p.m., it creates a schedule that starts dinner at 6:30 p.m. and finishes bathing at 7:30 p.m.

[1421] notification

[1422] The parent's smartphone (device) receives push notifications from the server and displays the schedule and advice on the app. For example, the app can display alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30." Parents can check the app's notifications and manage their children's lives according to the suggested schedule. This allows parents to prevent their children from getting enough sleep and ensure a healthy lifestyle.

[1423] Examples and prompts

[1424] For example, based on data recorded by an activity tracker, the following schedule could be sent to a parent's smartphone.

[1425] Example prompt:

[1426] "Analyze your child's sleep rhythm and create a timeline for optimal sleep onset."

[1427] This system allows parents to receive specific instructions in real time, such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath time at 19:30," enabling them to effectively manage their children's daily rhythms.

[1428] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1429] Step 1:

[1430] The server collects children's daily activity data from activity trackers and lifelogging applications. The collected data includes the number of steps, exercise volume, heart rate, meal times, bath time, etc. This data is sent to the server via the network. The input is the raw data from the activity trackers and lifelogging applications, which is then stored in a secure database.

[1431] Step 2:

[1432] The server cleanses the collected daily activity data. As part of the cleansing process, it corrects outliers and missing data to build an accurate dataset. Specifically, it performs operations such as deleting values ​​outside the data range and filling in missing values ​​with the average value. The input is the raw data collected in step 1, and the output is a cleansed, accurate dataset.

[1433] Step 3:

[1434] The server then uses machine learning algorithms to analyze the cleansed data. Specifically, it uses frameworks such as TensorFlow to analyze the child's sleep rhythm and sleep onset tendency. Data from the past few weeks is used as input to extract the child's average sleep onset time and sleep onset pattern. The output is the analysis results of sleep onset tendency and sleep onset pattern.

[1435] Step 4:

[1436] The server calculates the optimal time to fall asleep for that day based on the analysis results. It then works backwards from this optimal time to generate a preparation schedule before falling asleep. For example, if the optimal time to fall asleep is 8:30 p.m., it creates a timeline in which dinner starts at 6:30 p.m. and bathing finishes at 7:30 p.m. The input is the analysis results obtained in step 3, and the output is a specific preparation schedule.

[1437] Step 5:

[1438] The server pushes the generated preparation schedule to the user's device. Specifically, it sends notifications to the parent's smartphone with content such as "Start preparing dinner at 18:30," "Dinner at 19:00," and "Start preparing for bath at 19:30." The input is the preparation schedule generated in step 4, and the output is the notification content displayed on the user's device.

[1439] Step 6:

[1440] Users can check notifications on their smartphones and manage their children's lives according to the suggested schedule. For example, parents can ensure their children fall asleep at the optimal time by starting dinner preparation at 18:30, feeding them at 19:00, and starting bathing at 19:30. The input is the notification content on the device, and the output is the child's healthy lifestyle rhythm.

[1441] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1442] MODE FOR CARRYING OUT THE INVENTION

[1443] The present invention relates to a system for proposing an optimal time for a child to fall asleep, and embodiments thereof will be described below. In particular, by combining it with an emotion engine that recognizes the user's emotions, further effects can be provided.

[1444] System configuration

[1445] The system includes a means for collecting data on a child's daily activities, a means for analyzing the collected data, a means for generating a timeline from the analysis results, a means for notifying the user of the generated timeline, and an emotion engine for recognizing the user's emotions.

[1446] Specific examples of programs

[1447] 1. Data Collection

[1448] server

[1449] The server periodically collects the child's daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app.

[1450] The server stores the collected data in a secure database and performs data cleansing, correcting outliers and missing data to build an accurate data set.

[1451] 2. Data Analysis

[1452] server

[1453] The server analyzes the collected daily activity data using machine learning algorithms to analyze each child's individual sleep rhythm and sleep onset tendency.

[1454] For example, check for patterns of decreased heart rate or decreased exercise volume at certain times of the day.

[1455] 3. Calculating the optimal time to fall asleep

[1456] server

[1457] Based on the analysis results, the server calculates the optimal time to fall asleep for that day by combining the average time to fall asleep obtained from past data with the activity data for that day.

[1458] 4. Timeline generation

[1459] server

[1460] The server generates a timeline of preparations before falling asleep (eating, bathing, etc.) based on the optimal time to fall asleep.

[1461] For example, if you fall asleep at 8:30 p.m., create a timeline that includes dinner at 6:30 p.m. and bath time at 7:30 p.m.

[1462] 5. Emotional Engine Adjustment

[1463] server

[1464] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[1465] The server takes into account the emotion engine's analysis and fine-tunes the timeline, for example, if a child feels stressed during a certain time period, it will add relaxation activities during that time.

[1466] 6. Notification

[1467] Terminal

[1468] The parent's smartphone receives push notifications from the server and displays the schedule and advice on the app.

[1469] Specifically, alerts will be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[1470] 7. Feedback

[1471] User

[1472] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[1473] Parents engage in relaxation activities with their children (e.g., reading aloud, playing music).

[1474] Parents enter feedback into the app, reporting any problems encountered during implementation and their child's emotional state.

[1475] 8. Processing Feedback

[1476] server

[1477] The server receives feedback from the parents and stores it in a database.

[1478] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[1479] In this way, the system maintains an optimal sleep rhythm for children through collaboration between the server, device, and user, and enables flexible responses to emotional situations through the emotion engine, thereby realizing health management for children and the establishment of a comfortable daily rhythm.

[1480] The processing flow will be explained below.

[1481] Step 1:

[1482] User

[1483] Parents launch the smartphone app and set up their child's account by entering basic information such as their child's name, age, and gender.

[1484] Step 2:

[1485] Terminal

[1486] The parent's smartphone app syncs with the activity tracker, a wearable device worn by the child that collects data such as steps, exercise volume, and heart rate.

[1487] Step 3:

[1488] server

[1489] The server collects daily activity data (number of steps, amount of exercise, heart rate, meal times, bath time, etc.) from the activity tracker and smartphone app at regular intervals.

[1490] The server stores the collected data in a secure database, where it is cleansed and corrected for outliers and missing data.

[1491] Step 4:

[1492] server

[1493] The server analyzes the child's sleep rhythm and sleep onset patterns based on data from the past few weeks, and machine learning algorithms identify patterns of decreased heart rate and decreased physical activity at certain times of the day.

[1494] Step 5:

[1495] server

[1496] The server then uses the analysis results to calculate the optimal time to fall asleep for that day. Specifically, it predicts the average time to fall asleep obtained from past data by combining that day's activity data.

[1497] Step 6:

[1498] server

[1499] The server generates a timeline for preparations before falling asleep (e.g., meals and bathing) based on the optimal time to fall asleep. For example, if the patient falls asleep at 8:30 PM, the server creates a schedule for dinner at 6:30 PM and bathing at 7:30 PM.

[1500] Step 7:

[1501] server

[1502] The emotion engine collects the child's facial and voice data to recognize their emotions. For example, emotion data can be collected in real time through a camera or microphone.

[1503] The timeline is fine-tuned based on the emotion engine's analysis: for example, if a child is feeling stressed, add relaxation activities during that time.

[1504] Step 8:

[1505] server

[1506] The server pushes the generated timeline to the parent's smartphone.

[1507] Step 9:

[1508] Terminal

[1509] The parent's smartphone receives notifications from the server and displays schedules and advice on the app.

[1510] For example, alerts could be displayed in the form of "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[1511] Step 10:

[1512] User

[1513] Parents can check the app's notifications and manage their child's life according to the suggested schedule.

[1514] For example, start preparing dinner at 18:30, feed dinner at 19:00, and bathe at 19:30. Additionally, if your child is feeling stressed, engage in relaxation activities (e.g., reading aloud, playing music).

[1515] Step 11:

[1516] User

[1517] Parents enter feedback into the app, reporting ongoing issues and their child's emotional state.

[1518] Step 12:

[1519] server

[1520] The server receives the feedback from the parents and stores it in a database.

[1521] The server analyzes the feedback data and reflects it in future schedule suggestions and adjustments to the emotion engine.

[1522] This allows the system to help children maintain optimal sleep rhythms and parents to manage their children's lives at the appropriate time.The emotion engine also enables flexible responses according to emotional situations.

[1523] Example 2

[1524] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1525] Current child sleep schedule management systems do not adequately consider a child's individual sleep rhythm or emotional state. Furthermore, there are many challenges in analyzing collected data and reflecting it in the timeline. As a result, parents struggle to find the optimal time for their child to fall asleep, which can have a negative impact on the child's health. The present invention aims to flexibly adjust the optimal sleep time and timeline based on the child's daily activity data and emotional data, and provide parents with accurate notifications.

[1526] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting daily activity data of a child, means for cleansing the collected data and storing it in a database, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep from the analysis results, means for fine-tuning the generated timeline taking emotions into consideration, means for notifying the user's terminal of the generated timeline, and means for collecting and processing feedback from the user. This makes it possible to propose a flexible schedule according to the individual situation of each child, and ensure the optimal time for falling asleep.

[1527] "Children's daily activity data" is information about the activities that children perform in their daily lives, including the number of steps, amount of exercise, heart rate, meal times, bath times, and the like.

[1528] "Data cleansing" is the process of correcting outliers and missing data in collected data to build an accurate and usable dataset.

[1529] A "database" is a system for storing and managing collected data, allowing necessary information to be retrieved efficiently.

[1530] "Sleep rhythm" refers to a child's sleep-wake pattern over a period of time, a cycle based on their natural biological clock.

[1531] "Sleep onset tendency" refers to the pattern or tendency of when and under what circumstances a child falls asleep.

[1532] A "timeline" is a timetable that indicates the best times to perform certain events or activities, including preparation steps before falling asleep.

[1533] The "emotion engine" is a system that recognizes emotions from a child's facial expressions and voice data, allowing it to analyze their emotional state.

[1534] "Fine-tuning" means flexibly modifying the generated timeline based on new information such as the analysis results of the emotion engine.

[1535] A "terminal" is a device that receives notifications and information from a server and displays them to the user, and includes smartphones, tablets, etc.

[1536] "Feedback" refers to opinions and impressions provided by users, as well as information about problems and emotional states during execution.

[1537] A "machine learning algorithm" is a computational method that automatically learns specific patterns and trends from data and makes predictions and classifications for new data.

[1538] The present invention provides a system for proposing an optimal sleep time for a child, and an embodiment thereof will be described in detail below. The system collects and analyzes a child's daily activity data to generate an optimal sleep time and a timeline for achieving this. It also includes a means for appropriately adjusting the timeline, taking into account the child's emotional state. This system promotes health management and optimization of the child's daily rhythm.

[1539] System configuration

[1540] The system consists of the following main components:

[1541] 1. Means of collecting data on children's daily activities

[1542] 2. How to cleanse and store the collected data in a database

[1543] 3. A means of analyzing children's sleep rhythms and sleep onset tendencies based on collected data

[1544] 4. A method for generating a timeline of preparations before falling asleep from the analysis results

[1545] 5. A means to collect emotional data and fine-tune the timeline through an emotional engine

[1546] 6. A method for notifying the user of the generated timeline

[1547] 7. How to collect and process user feedback

[1548] Data Collection and Cleansing

[1549] server

[1550] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and lifelogging applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath times, etc. The collected data is stored in a secure database. A data cleansing process corrects outliers and missing data to build an accurate dataset.

[1551] Data analysis and calculation of optimal sleep onset time

[1552] server

[1553] The server analyzes the collected daily activity data using machine learning algorithms (e.g., random forests and neural networks). This analysis allows the server to understand the child's sleep rhythm and sleep onset tendency. For example, it identifies patterns of decreased heart rate and reduced physical activity at certain times of the day. Based on this, the server calculates the optimal time for the child to fall asleep.

[1554] Creating and adjusting timelines

[1555] server

[1556] The server generates a timeline based on the optimal time to fall asleep, including preparation steps before falling asleep (e.g., dinner, bath, etc.). For example, to fall asleep at 8:30 p.m., it creates a schedule such as dinner at 6:30 p.m. and bath time at 7:30 p.m. Furthermore, it analyzes emotional data collected by the emotion engine (e.g., obtained using a camera or microphone) and fine-tunes the timeline. If a child feels stressed in the evening, it adds relaxation activities (e.g., listening to music) to that time period.

[1557] Schedule notifications and feedback

[1558] Terminal

[1559] The parent's smartphone receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath time at 19:30," and "Relaxation time at 20:00." Users can enter feedback through the app to report any problems encountered during execution and their child's emotional state.

[1560] server

[1561] The server stores and analyzes parent feedback in a database. This feedback data is used to improve future schedule suggestions and adjust the emotion engine. For example, the effectiveness of relaxation activities can be evaluated to improve the accuracy of future suggestions.

[1562] Examples of concrete examples and prompts

[1563] For example, the following prompt sentence is input to the generative AI model:

[1564] "My child has been waking up late recently. Can you suggest an optimal time for him to fall asleep?"

[1565] "Tell me about relaxation activities to help reduce my child's stress levels."

[1566] This system allows the server, device, and user to work together to maintain a child's optimal sleep rhythm and respond flexibly to their emotional state, thereby helping to manage a child's health and establishing a comfortable daily rhythm.

[1567] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1568] Step 1:

[1569] Data collection

[1570] server

[1571] The server periodically collects children's daily activity data from activity trackers (e.g., Fitbit, Apple Watch) and life log applications. This data includes the number of steps taken, exercise volume, heart rate, meal times, bath time, etc. Specifically, the server obtains data from each device through an API and stores it in a secure database.

[1572] Input: Raw data from activity trackers and life logging applications

[1573] Output: Daily activity data stored in a secure database

[1574] Step 2:

[1575] Data Cleansing

[1576] server

[1577] The server then performs data cleansing on the collected daily activity data. It detects outliers and missing data and corrects or removes them. This process uses statistical methods and heuristic rules. For example, extremely high heart rates and unnatural step counts are treated as outliers.

[1578] Input: Raw data stored in a database

[1579] Output: A cleansed, highly accurate dataset

[1580] Step 3:

[1581] Data analysis

[1582] server

[1583] The server uses the cleansed data to analyze the child's sleep rhythm and sleep onset trends. It uses machine learning algorithms (e.g., random forests, neural networks) to extract patterns and analyze trends. For example, it identifies patterns of decreased heart rate at certain times of the day or periods of reduced physical activity.

[1584] Input: Cleansed dataset

[1585] Output: Analysis results (child's sleep rhythm and tendency to fall asleep)

[1586] Step 4:

[1587] Calculating the optimal time to fall asleep

[1588] server

[1589] The server then calculates the optimal time to fall asleep for that day based on the analysis results. It makes the prediction by combining the average time to fall asleep obtained from past data with the activity data for that day. For example, if you exercise a lot that day, it will set an earlier time to fall asleep.

[1590] Input: Analysis results and activity data for the day

[1591] Output: Optimal sleep time

[1592] Step 5:

[1593] Timeline Generation

[1594] server

[1595] The server generates a timeline of preparation steps (e.g., dinner, bath, etc.) before falling asleep based on the optimal time to fall asleep. For example, if the time to fall asleep is 8:30 PM, it creates a schedule for dinner at 6:30 PM and bath time at 7:30 PM. Specifically, the server uses rule-based logic to build the timeline.

[1596] Input: Optimal time to fall asleep

[1597] Output: Generated timeline

[1598] Step 6:

[1599] Emotional engine regulation

[1600] server

[1601] The server uses an emotion engine to collect the child's facial expressions and voice data and analyze their emotions. Based on real-time data acquired through the camera and microphone, the server evaluates the child's emotional state, reflects this in the timeline, and adds relaxation activities as needed.

[1602] Input: Generated timeline and emotion data

[1603] Output: Adjusted timeline that takes emotions into account

[1604] Step 7:

[1605] notification

[1606] Terminal

[1607] The device (parent's smartphone) receives push notifications from the server and displays schedules and advice on the app. Specifically, it displays alerts such as "Start preparing dinner at 18:30," "Dinner at 19:00," "Start preparing for bath at 19:30," and "Relaxation time at 20:00."

[1608] Input: Adjusted timeline

[1609] Output: Schedule and advice displayed on the smartphone app

[1610] Step 8:

[1611] feedback

[1612] User

[1613] The user (parent) checks the app's notifications, manages their child's life according to the suggested schedule, actually performs relaxation activities (e.g., reading aloud, playing music), and enters the results as feedback into the app.

[1614] Input: Implemented schedule and feedback

[1615] Output: Feedback data entered into the app

[1616] Step 9:

[1617] Processing Feedback

[1618] server

[1619] The server stores and analyzes user feedback in a database, and uses the feedback data to make future schedule suggestions and adjust the emotion engine.

[1620] Input: Feedback data

[1621] Output: Improved proposal and adjusted schedule

[1622] (Application example 2)

[1623] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1624] In recent years, there has been a surge in interest in children's sleep rhythms and emotional lifestyle management. However, existing systems only provide an appropriate timeline for sleep onset based on daily activity data, and are unable to respond to real-time emotional changes. This makes it difficult to respond appropriately to stress or discomfort felt at specific times, posing challenges to children's health management and maintaining a comfortable lifestyle.

[1625] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on the child's daily activities, means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data, means for generating a timeline of preparations before falling asleep based on the analysis results, means for an emotion engine to collect data on the child's facial expressions and voice and recognize emotions, means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine, and means for notifying the user's terminal of the generated timeline. This makes it possible to manage the child's health and maintain a comfortable lifestyle by suggesting an optimal time to fall asleep while responding to emotional changes in real time.

[1626] "Means for collecting children's daily activity data" refers to devices or software that use activity trackers or life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.).

[1627] "Means for analyzing a child's sleep rhythm and sleep onset tendency based on collected data" refers to devices or programs that use collected daily activity data to analyze a child's individual sleep rhythm and sleep onset tendency through machine learning algorithms and statistical methods.

[1628] "Means for generating a timeline of preparations before falling asleep from the analysis results" refers to a device or program that determines the optimal time for a child to fall asleep based on the analyzed data and generates a schedule of the specific preparatory actions (e.g., meals, bathing, relaxation) required to reach that time.

[1629] "Means for the emotion engine to collect the child's facial expressions and voice data and recognize emotions" refers to devices or programs that collect the child's facial expressions and voice data in real time through a camera or microphone, and analyze this data to determine the child's emotional state.

[1630] The "means for fine-tuning the timeline based on the generated timeline and the analysis results of the emotion engine" refers to a device or program that combines a pre-sleep timeline that has been generated in advance with the analysis results of the emotion engine, and adds relaxation activities or other adjustments to the timeline as necessary.

[1631] "Means for notifying the user of the generated timeline" refers to a system or program for notifying the parent or user of the final adjusted timeline on their device, such as a smartphone or tablet.

[1632] The present invention relates to a system for suggesting an optimal time for a child to fall asleep. In particular, this embodiment shows a system that combines a child's daily activity data with real-time emotional data to generate an optimal timeline and notify a parent or user. As a novel application example, a system that suggests optimal work break times to maximize the work efficiency of robots in a factory is also considered.

[1633] System configuration:

[1634] 1. Data collection methods:

[1635] The server uses activity trackers and life log applications to collect data on children's daily activities (number of steps, amount of exercise, heart rate, meal times, bath times, etc.) It also collects data from various sensors (vibration sensors, temperature sensors, operating time sensors, etc.) attached to robots in the factory.

[1636] 2. Data analysis methods:

[1637] The server analyzes the collected data to track the sleep rhythms and sleep onset patterns of the child and robot, as well as their work performance. This analysis uses Python-based machine learning algorithms (such as Scikit-learn and TensorFlow) to identify individual trends.

[1638] 3. Timeline generation method:

[1639] Based on the analysis results, the server calculates optimal times for falling asleep and resting, and generates specific preparation actions and schedules to achieve these times. The generated timeline includes preparation times before falling asleep (eating, bathing, relaxation, etc.) for children, and optimal work breaks and work schedules for robots.

[1640] 4. How to recognize emotions:

[1641] The emotion engine collects facial and voice data from the child and robot via the camera and microphone, and recognizes their emotions using facial recognition and voice analysis libraries (OpenCV, Google Cloud Speech-to-Text, etc.).

[1642] 5. Timeline fine-tuning methods:

[1643] The server fine-tunes the timeline based on the generated timeline and the analysis results of the emotion engine. For example, if a child feels stressed during a certain time period, it will add relaxation activities to that time period, or if the robot's task performance is declining, it will suggest a break.

[1644] 6. Means of notification:

[1645] The server then notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device, including specific schedules and advice.

[1646] Examples:

[1647] The automated transport robots in Factory A use vibration and temperature sensors to collect operational data, which is then analyzed using a Python-based machine learning algorithm. The resulting analysis results are used by a server to generate optimal work break times and schedules. The robots also monitor their surroundings using cameras and microphones, recognizing real-time emotional data and fine-tuning their timelines. The adjusted timelines are then sent to the factory's display system and the managers' smartphones.

[1648] Example prompt sentence:

[1649] "Factory A's automated transport robots collect operational data using vibration and temperature sensors. Based on this data, generate Python code that suggests optimal work schedules and break times. The code should also include an analysis section using a machine learning algorithm."

[1650] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1651] Step 1:

[1652] Collect daily activity data of children and robots.

[1653] The server collects data from activity trackers, life log applications, and various sensors in the factory. This data includes the number of steps, exercise volume, heart rate, meal times, bath times, vibration, temperature, and sound. Input data is acquired from each sensor in real time and sent to the server, which then stores this data in temporary data storage.

[1654] Step 2:

[1655] The collected data is cleansed and stored in a database.

[1656] The server cleanses the temporarily stored data. This process corrects outliers and missing data to ensure data accuracy and consistency. Specifically, it filters out, for example, extremely high heart rates and abnormally long periods of inactivity. After the cleansing process is complete, the server stores the clean dataset in a secure database. The input data is the temporarily stored raw data, and the output data is the cleansed data.

[1657] Step 3:

[1658] The collected data is used to analyze the sleep rhythms and sleep onset tendencies of children and robots, as well as their work performance.

[1659] The server uses the cleansed data and applies machine learning algorithms (e.g., Scikit-learn or TensorFlow) to perform analysis. The input data is the cleansed activity data and sensor data, and the output data is the analysis results that indicate individual sleep rhythms and work performance. Specifically, it analyzes changes in heart rate patterns and exercise volume to identify the logic behind abnormalities.

[1660] Step 4:

[1661] The analysis results are used to generate a timeline for preparation before falling asleep, or a schedule for rest and work.

[1662] Based on the collected and analyzed data, the server generates a timeline that includes the optimal time for the child to fall asleep and the optimal time for the robot to rest. The input data is the analysis result, and the output data is a specific timeline schedule. For example, if the child falls asleep at 8:30 PM, a timeline is generated that includes dinner at 6:30 PM and bath time at 7:30 PM. Similarly, optimal rest times and work schedules are also calculated based on the robot's operating data.

[1663] Step 5:

[1664] The emotion engine collects facial and voice data from children and robots to recognize their emotions.

[1665] The server uses real-time facial and voice data collected through cameras and microphones and analyzes it using an emotion engine. The input data is the facial and voice data collected in real time, and the output data is the emotion analysis results. Specifically, it uses facial recognition software (such as OpenCV) and voice analysis libraries (such as Google Cloud Speech-to-Text) to determine the stress level and discomfort of children and robots.

[1666] Step 6:

[1667] Fine-tune the timeline based on the analysis results of the emotion engine.

[1668] The server incorporates the emotion engine's analysis results into the generated timeline and fine-tunes it as needed. For example, if a child feels stressed during a certain time period, it can add relaxation activities to that time period, or if a robot's work performance is declining, it can add rest periods. The input data are the emotion engine's analysis results and the existing timeline, and the output data is the fine-tuned timeline.

[1669] Step 7:

[1670] The final adjusted timeline is notified to the user's terminal.

[1671] The server notifies the parent or user of the final adjusted timeline via their smartphone, tablet, or other device. The input data is the final adjusted timeline, and the output data is a schedule notification displayed on the user's device. Specifically, push notifications and alerts are sent to smartphone apps and display systems within the factory. This allows users to receive visual instructions and take appropriate action.

[1672] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1673] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1674] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1675] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1676] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1677] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1678] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1679] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1680] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1681] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1682] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1683] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1684] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1685] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1686] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1687] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1688] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1689] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1690] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1691] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1692] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1693] The following is further disclosed regarding the above embodiment.

[1694] (Claim 1)

[1695] A system for suggesting an optimal sleep time for a child, comprising:

[1696] a means of collecting data on children's daily activities;

[1697] A means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data;

[1698] A means for generating a timeline of preparations before falling asleep from the analysis results;

[1699] A means for notifying a user's terminal of the generated timeline;

[1700] A system including:

[1701] (Claim 2)

[1702] 10. The system of claim 1, wherein the means for collecting the child's activity data is an activity tracker and a life log application.

[1703] (Claim 3)

[1704] 2. The system according to claim 1, further comprising: cleansing the collected data and storing it in a database.

[1705] "Example 1"

[1706] (Claim 1)

[1707] A system for suggesting an optimal sleep time for a child, comprising:

[1708] a means of collecting data on children's daily activities;

[1709] A means for cleansing the collected data and storing it in a database;

[1710] A means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data;

[1711] A means for calculating the optimal time to fall asleep from the analysis results and generating a timeline for preparations before falling asleep;

[1712] A means for notifying a user's terminal of the generated timeline;

[1713] a means for sending notifications based on the timeline to encourage the user to prepare their child for sleep;

[1714] A system including:

[1715] (Claim 2)

[1716] 10. The system of claim 1, wherein the means for collecting the child's activity data is an activity tracker and a life log application.

[1717] (Claim 3)

[1718] 2. The system according to claim 1, wherein the analysis uses a machine learning algorithm.

[1719] "Application Example 1"

[1720] New Claims

[1721] (Claim 1)

[1722] A system for suggesting an optimal sleep time for a child, comprising:

[1723] a means of collecting data on children's daily activities;

[1724] A means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data;

[1725] A means for generating a timeline of preparations before falling asleep from the analysis results;

[1726] A means for notifying a user's terminal of the generated timeline;

[1727] A means for sending a push notification to a user's device;

[1728] a means of analyzing the data using machine learning algorithms;

[1729] A system including:

[1730] (Claim 2)

[1731] 10. The system of claim 1, wherein the means for collecting the child's activity data is an activity tracker and a life log application.

[1732] (Claim 3)

[1733] 2. The system according to claim 1, further comprising: cleansing the collected data and storing it in a database.

[1734] "Example 2: Combining Emotion Engines"

[1735] (Claim 1)

[1736] A system for suggesting an optimal sleep time for a child, comprising:

[1737] a means of collecting data on children's daily activities;

[1738] means for cleansing and storing the collected data in a database;

[1739] A means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data;

[1740] A means for generating a timeline of preparations before falling asleep from the analysis results;

[1741] A means to fine-tune the generated timeline with consideration of emotions;

[1742] A means for notifying a user's terminal of the generated timeline;

[1743] a means for collecting and processing user feedback;

[1744] A system including:

[1745] (Claim 2)

[1746] 10. The system of claim 1, wherein the means for collecting the child's activity data is an activity tracker and a life log application.

[1747] (Claim 3)

[1748] The system according to claim 1, characterized in that it uses an emotion engine to collect emotional data of children and reflect it on the timeline.

[1749] "Application example 2 when combining emotion engines"

[1750] (Claim 1)

[1751] A system for suggesting an optimal sleep time for a child, comprising:

[1752] a means of collecting data on children's daily activities;

[1753] A means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data;

[1754] A means for generating a timeline of preparations before falling asleep from the analysis results;

[1755] The emotion engine collects facial and voice data from children and recognizes their emotions.

[1756] A means for fine-tuning the timeline based on the generated timeline and the analysis result of the emotion engine;

[1757] A means for notifying a user's terminal of the generated timeline;

[1758] A system including:

[1759] (Claim 2)

[1760] 10. The system of claim 1, wherein the means for collecting the child's activity data is an activity tracker and a life log application.

[1761] (Claim 3)

[1762] 2. The system according to claim 1, further comprising: cleansing the collected data and storing it in a database. [Explanation of symbols]

[1763] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system for suggesting an optimal sleep time for a child, comprising: a means of collecting data on children's daily activities; A means for analyzing the child's sleep rhythm and sleep onset tendency based on the collected data; A means for generating a timeline of preparations before falling asleep from the analysis results; A means for notifying a user's terminal of the generated timeline; A system including:

2. 10. The system of claim 1, wherein the means for collecting the child's activity data is an activity tracker and a life log application.

3. 2. The system according to claim 1, further comprising: cleansing the collected data and storing the data in a database.

Images